mirror of
https://github.com/HumanAIGC-Engineering/gradio-webrtc.git
synced 2026-02-04 17:39:23 +08:00
Working draft
This commit is contained in:
freddyaboulton
14
.gitignore
vendored
Normal file
14
.gitignore
vendored
Normal file
@@ -0,0 +1,14 @@
|
||||
.eggs/
|
||||
dist/
|
||||
*.pyc
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
__tmp/*
|
||||
*.pyi
|
||||
.mypycache
|
||||
.ruff_cache
|
||||
node_modules
|
||||
backend/**/templates/
|
||||
demo/MobileNetSSD_deploy.caffemodel
|
||||
demo/MobileNetSSD_deploy.prototxt.txt
|
||||
469
README.md
Normal file
469
README.md
Normal file
@@ -0,0 +1,469 @@
|
||||
---
|
||||
tags: [gradio-custom-component, Video, streaming, webrtc, realtime]
|
||||
title: gradio_webrtc
|
||||
short_description: Stream images in realtime with webrtc
|
||||
colorFrom: blue
|
||||
colorTo: yellow
|
||||
sdk: gradio
|
||||
pinned: false
|
||||
app_file: space.py
|
||||
---
|
||||
|
||||
# `gradio_webrtc`
|
||||
<img alt="Static Badge" src="https://img.shields.io/badge/version%20-%200.0.1%20-%20orange">
|
||||
|
||||
Stream images in realtime with webrtc
|
||||
|
||||
## Installation
|
||||
|
||||
```bash
|
||||
pip install gradio_webrtc
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
import gradio as gr
|
||||
import cv2
|
||||
import numpy as np
|
||||
from gradio_webrtc import WebRTC
|
||||
from pathlib import Path
|
||||
|
||||
CLASSES = [
|
||||
"background",
|
||||
"aeroplane",
|
||||
"bicycle",
|
||||
"bird",
|
||||
"boat",
|
||||
"bottle",
|
||||
"bus",
|
||||
"car",
|
||||
"cat",
|
||||
"chair",
|
||||
"cow",
|
||||
"diningtable",
|
||||
"dog",
|
||||
"horse",
|
||||
"motorbike",
|
||||
"person",
|
||||
"pottedplant",
|
||||
"sheep",
|
||||
"sofa",
|
||||
"train",
|
||||
"tvmonitor",
|
||||
]
|
||||
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
|
||||
|
||||
directory = Path(__file__).parent
|
||||
|
||||
MODEL = str((directory / "MobileNetSSD_deploy.caffemodel").resolve())
|
||||
PROTOTXT = str((directory / "MobileNetSSD_deploy.prototxt.txt").resolve())
|
||||
net = cv2.dnn.readNetFromCaffe(PROTOTXT, MODEL)
|
||||
|
||||
|
||||
def detection(image, conf_threshold=0.3):
|
||||
|
||||
blob = cv2.dnn.blobFromImage(
|
||||
cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5
|
||||
)
|
||||
net.setInput(blob)
|
||||
|
||||
detections = net.forward()
|
||||
image = cv2.resize(image, (500, 500))
|
||||
(h, w) = image.shape[:2]
|
||||
labels = []
|
||||
for i in np.arange(0, detections.shape[2]):
|
||||
confidence = detections[0, 0, i, 2]
|
||||
|
||||
if confidence > conf_threshold:
|
||||
# extract the index of the class label from the `detections`,
|
||||
# then compute the (x, y)-coordinates of the bounding box for
|
||||
# the object
|
||||
idx = int(detections[0, 0, i, 1])
|
||||
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
|
||||
(startX, startY, endX, endY) = box.astype("int")
|
||||
|
||||
# display the prediction
|
||||
label = f"{CLASSES[idx]}: {round(confidence * 100, 2)}%"
|
||||
labels.append(label)
|
||||
cv2.rectangle(image, (startX, startY), (endX, endY), COLORS[idx], 2)
|
||||
y = startY - 15 if startY - 15 > 15 else startY + 15
|
||||
cv2.putText(
|
||||
image, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2
|
||||
)
|
||||
return image
|
||||
|
||||
|
||||
css=""".my-group {max-width: 600px !important; max-height: 600 !important;}
|
||||
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
|
||||
|
||||
|
||||
with gr.Blocks(css=css) as demo:
|
||||
gr.HTML(
|
||||
"""
|
||||
<h1 style='text-align: center'>
|
||||
YOLOv10 Webcam Stream
|
||||
</h1>
|
||||
""")
|
||||
gr.HTML(
|
||||
"""
|
||||
<h3 style='text-align: center'>
|
||||
<a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
|
||||
</h3>
|
||||
""")
|
||||
with gr.Column(elem_classes=["my-column"]):
|
||||
with gr.Group(elem_classes=["my-group"]):
|
||||
image = WebRTC(label="Strean")
|
||||
conf_threshold = gr.Slider(
|
||||
label="Confidence Threshold",
|
||||
minimum=0.0,
|
||||
maximum=1.0,
|
||||
step=0.05,
|
||||
value=0.30,
|
||||
)
|
||||
|
||||
image.webrtc_stream(
|
||||
fn=detection,
|
||||
inputs=[image],
|
||||
stream_every=0.05,
|
||||
time_limit=30
|
||||
)
|
||||
|
||||
if __name__ == '__main__':
|
||||
demo.launch()
|
||||
|
||||
```
|
||||
|
||||
## `WebRTC`
|
||||
|
||||
### Initialization
|
||||
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th align="left">name</th>
|
||||
<th align="left" style="width: 25%;">type</th>
|
||||
<th align="left">default</th>
|
||||
<th align="left">description</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td align="left"><code>value</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
str
|
||||
| Path
|
||||
| tuple[str | Path, str | Path | None]
|
||||
| Callable
|
||||
| None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">path or URL for the default value that WebRTC component is going to take. Can also be a tuple consisting of (video filepath, subtitle filepath). If a subtitle file is provided, it should be of type .srt or .vtt. Or can be callable, in which case the function will be called whenever the app loads to set the initial value of the component.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>height</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
int | str | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">The height of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>width</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
int | str | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">The width of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>label</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
str | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">the label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>every</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
Timer | float | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">continously calls `value` to recalculate it if `value` is a function (has no effect otherwise). Can provide a Timer whose tick resets `value`, or a float that provides the regular interval for the reset Timer.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>inputs</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
Component | Sequence[Component] | set[Component] | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">components that are used as inputs to calculate `value` if `value` is a function (has no effect otherwise). `value` is recalculated any time the inputs change.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>show_label</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">if True, will display label.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>container</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>True</code></td>
|
||||
<td align="left">if True, will place the component in a container - providing some extra padding around the border.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>scale</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
int | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>min_width</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
int
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>160</code></td>
|
||||
<td align="left">minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>interactive</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">if True, will allow users to upload a video; if False, can only be used to display videos. If not provided, this is inferred based on whether the component is used as an input or output.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>visible</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>True</code></td>
|
||||
<td align="left">if False, component will be hidden.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>elem_id</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
str | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">an optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>elem_classes</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
list[str] | str | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">an optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>render</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>True</code></td>
|
||||
<td align="left">if False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>key</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
int | str | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">if assigned, will be used to assume identity across a re-render. Components that have the same key across a re-render will have their value preserved.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>mirror_webcam</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>True</code></td>
|
||||
<td align="left">if True webcam will be mirrored. Default is True.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>show_share_button</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">if True, will show a share icon in the corner of the component that allows user to share outputs to Hugging Face Spaces Discussions. If False, icon does not appear. If set to None (default behavior), then the icon appears if this Gradio app is launched on Spaces, but not otherwise.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>show_download_button</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">if True, will show a download icon in the corner of the component that allows user to download the output. If False, icon does not appear. By default, it will be True for output components and False for input components.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>min_length</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
int | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">the minimum length of video (in seconds) that the user can pass into the prediction function. If None, there is no minimum length.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>max_length</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
int | None
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>None</code></td>
|
||||
<td align="left">the maximum length of video (in seconds) that the user can pass into the prediction function. If None, there is no maximum length.</td>
|
||||
</tr>
|
||||
|
||||
<tr>
|
||||
<td align="left"><code>streaming</code></td>
|
||||
<td align="left" style="width: 25%;">
|
||||
|
||||
```python
|
||||
bool
|
||||
```
|
||||
|
||||
</td>
|
||||
<td align="left"><code>False</code></td>
|
||||
<td align="left">when used set as an output, takes video chunks yielded from the backend and combines them into one streaming video output. Each chunk should be a video file with a .ts extension using an h.264 encoding. Mp4 files are also accepted but they will be converted to h.264 encoding.</td>
|
||||
</tr>
|
||||
</tbody></table>
|
||||
|
||||
|
||||
### Events
|
||||
|
||||
| name | description |
|
||||
|:-----|:------------|
|
||||
| `tick` | |
|
||||
|
||||
|
||||
|
||||
### User function
|
||||
|
||||
The impact on the users predict function varies depending on whether the component is used as an input or output for an event (or both).
|
||||
|
||||
- When used as an Input, the component only impacts the input signature of the user function.
|
||||
- When used as an output, the component only impacts the return signature of the user function.
|
||||
|
||||
The code snippet below is accurate in cases where the component is used as both an input and an output.
|
||||
|
||||
- **As output:** Is passed, passes the uploaded video as a `str` filepath or URL whose extension can be modified by `format`.
|
||||
- **As input:** Should return, expects a {str} or {pathlib.Path} filepath to a video which is displayed, or a {Tuple[str | pathlib.Path, str | pathlib.Path | None]} where the first element is a filepath to a video and the second element is an optional filepath to a subtitle file.
|
||||
|
||||
```python
|
||||
def predict(
|
||||
value: str
|
||||
) -> typing.Any:
|
||||
return value
|
||||
```
|
||||
|
||||
4
backend/gradio_webrtc/__init__.py
Normal file
4
backend/gradio_webrtc/__init__.py
Normal file
@@ -0,0 +1,4 @@
|
||||
|
||||
from .webrtc import WebRTC
|
||||
|
||||
__all__ = ['WebRTC']
|
||||
315
backend/gradio_webrtc/webrtc.py
Normal file
315
backend/gradio_webrtc/webrtc.py
Normal file
@@ -0,0 +1,315 @@
|
||||
"""gr.Video() component."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import Callable, Sequence
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any, Literal, Optional, cast
|
||||
|
||||
|
||||
from aiortc import RTCPeerConnection, RTCSessionDescription
|
||||
from aiortc.contrib.media import MediaRelay
|
||||
from aiortc import VideoStreamTrack
|
||||
from aiortc.mediastreams import MediaStreamError
|
||||
from aiortc.contrib.media import VideoFrame # type: ignore
|
||||
from gradio_client import handle_file
|
||||
import numpy as np
|
||||
|
||||
|
||||
from gradio import utils, wasm_utils
|
||||
from gradio.components.base import Component, server
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from gradio.components import Timer
|
||||
from gradio.blocks import Block
|
||||
|
||||
|
||||
if wasm_utils.IS_WASM:
|
||||
raise ValueError("Not supported in gradio-lite!")
|
||||
|
||||
|
||||
|
||||
class VideoCallback(VideoStreamTrack):
|
||||
"""
|
||||
This works for streaming input and output
|
||||
"""
|
||||
|
||||
kind = "video"
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
track,
|
||||
event_handler: Callable,
|
||||
) -> None:
|
||||
super().__init__() # don't forget this!
|
||||
self.track = track
|
||||
self.event_handler = event_handler
|
||||
self.latest_args: str | list[Any] = "not_set"
|
||||
|
||||
def add_frame_to_payload(self, args: list[Any], frame: np.ndarray | None) -> list[Any]:
|
||||
new_args = []
|
||||
for val in args:
|
||||
if isinstance(val, str) and val == "__webrtc_value__":
|
||||
new_args.append(frame)
|
||||
else:
|
||||
new_args.append(val)
|
||||
return new_args
|
||||
|
||||
|
||||
def array_to_frame(self, array: np.ndarray) -> VideoFrame:
|
||||
return VideoFrame.from_ndarray(array, format="bgr24")
|
||||
|
||||
async def recv(self):
|
||||
try:
|
||||
|
||||
try:
|
||||
frame = await self.track.recv()
|
||||
except MediaStreamError:
|
||||
return
|
||||
frame_array = frame.to_ndarray(format="bgr24")
|
||||
|
||||
if self.latest_args == "not_set":
|
||||
print("args not set")
|
||||
return frame
|
||||
|
||||
|
||||
args = self.add_frame_to_payload(self.latest_args, frame_array)
|
||||
|
||||
array = self.event_handler(*args)
|
||||
|
||||
new_frame = self.array_to_frame(array)
|
||||
if frame:
|
||||
new_frame.pts = frame.pts
|
||||
new_frame.time_base = frame.time_base
|
||||
else:
|
||||
pts, time_base = await self.next_timestamp()
|
||||
new_frame.pts = pts
|
||||
new_frame.time_base = time_base
|
||||
|
||||
return new_frame
|
||||
except Exception as e:
|
||||
print(e)
|
||||
import traceback
|
||||
|
||||
traceback.print_exc()
|
||||
|
||||
|
||||
class WebRTC(Component):
|
||||
"""
|
||||
Creates a video component that can be used to upload/record videos (as an input) or display videos (as an output).
|
||||
For the video to be playable in the browser it must have a compatible container and codec combination. Allowed
|
||||
combinations are .mp4 with h264 codec, .ogg with theora codec, and .webm with vp9 codec. If the component detects
|
||||
that the output video would not be playable in the browser it will attempt to convert it to a playable mp4 video.
|
||||
If the conversion fails, the original video is returned.
|
||||
|
||||
Demos: video_identity_2
|
||||
"""
|
||||
|
||||
pcs: set[RTCPeerConnection] = set([])
|
||||
relay = MediaRelay()
|
||||
connections: dict[str, VideoCallback] = {}
|
||||
|
||||
EVENTS = [
|
||||
"tick"
|
||||
]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
value: str
|
||||
| Path
|
||||
| tuple[str | Path, str | Path | None]
|
||||
| Callable
|
||||
| None = None,
|
||||
*,
|
||||
height: int | str | None = None,
|
||||
width: int | str | None = None,
|
||||
label: str | None = None,
|
||||
every: Timer | float | None = None,
|
||||
inputs: Component | Sequence[Component] | set[Component] | None = None,
|
||||
show_label: bool | None = None,
|
||||
container: bool = True,
|
||||
scale: int | None = None,
|
||||
min_width: int = 160,
|
||||
interactive: bool | None = None,
|
||||
visible: bool = True,
|
||||
elem_id: str | None = None,
|
||||
elem_classes: list[str] | str | None = None,
|
||||
render: bool = True,
|
||||
key: int | str | None = None,
|
||||
mirror_webcam: bool = True,
|
||||
show_share_button: bool | None = None,
|
||||
show_download_button: bool | None = None,
|
||||
min_length: int | None = None,
|
||||
max_length: int | None = None,
|
||||
streaming: bool = False,
|
||||
):
|
||||
"""
|
||||
Parameters:
|
||||
value: path or URL for the default value that WebRTC component is going to take. Can also be a tuple consisting of (video filepath, subtitle filepath). If a subtitle file is provided, it should be of type .srt or .vtt. Or can be callable, in which case the function will be called whenever the app loads to set the initial value of the component.
|
||||
format: the file extension with which to save video, such as 'avi' or 'mp4'. This parameter applies both when this component is used as an input to determine which file format to convert user-provided video to, and when this component is used as an output to determine the format of video returned to the user. If None, no file format conversion is done and the video is kept as is. Use 'mp4' to ensure browser playability.
|
||||
height: The height of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.
|
||||
width: The width of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.
|
||||
label: the label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.
|
||||
every: continously calls `value` to recalculate it if `value` is a function (has no effect otherwise). Can provide a Timer whose tick resets `value`, or a float that provides the regular interval for the reset Timer.
|
||||
inputs: components that are used as inputs to calculate `value` if `value` is a function (has no effect otherwise). `value` is recalculated any time the inputs change.
|
||||
show_label: if True, will display label.
|
||||
container: if True, will place the component in a container - providing some extra padding around the border.
|
||||
scale: relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.
|
||||
min_width: minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.
|
||||
interactive: if True, will allow users to upload a video; if False, can only be used to display videos. If not provided, this is inferred based on whether the component is used as an input or output.
|
||||
visible: if False, component will be hidden.
|
||||
elem_id: an optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.
|
||||
elem_classes: an optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.
|
||||
render: if False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.
|
||||
key: if assigned, will be used to assume identity across a re-render. Components that have the same key across a re-render will have their value preserved.
|
||||
mirror_webcam: if True webcam will be mirrored. Default is True.
|
||||
include_audio: whether the component should record/retain the audio track for a video. By default, audio is excluded for webcam videos and included for uploaded videos.
|
||||
autoplay: whether to automatically play the video when the component is used as an output. Note: browsers will not autoplay video files if the user has not interacted with the page yet.
|
||||
show_share_button: if True, will show a share icon in the corner of the component that allows user to share outputs to Hugging Face Spaces Discussions. If False, icon does not appear. If set to None (default behavior), then the icon appears if this Gradio app is launched on Spaces, but not otherwise.
|
||||
show_download_button: if True, will show a download icon in the corner of the component that allows user to download the output. If False, icon does not appear. By default, it will be True for output components and False for input components.
|
||||
min_length: the minimum length of video (in seconds) that the user can pass into the prediction function. If None, there is no minimum length.
|
||||
max_length: the maximum length of video (in seconds) that the user can pass into the prediction function. If None, there is no maximum length.
|
||||
loop: if True, the video will loop when it reaches the end and continue playing from the beginning.
|
||||
streaming: when used set as an output, takes video chunks yielded from the backend and combines them into one streaming video output. Each chunk should be a video file with a .ts extension using an h.264 encoding. Mp4 files are also accepted but they will be converted to h.264 encoding.
|
||||
watermark: an image file to be included as a watermark on the video. The image is not scaled and is displayed on the bottom right of the video. Valid formats for the image are: jpeg, png.
|
||||
"""
|
||||
self.height = height
|
||||
self.width = width
|
||||
self.mirror_webcam = mirror_webcam
|
||||
self.concurrency_limit = 1
|
||||
self.show_share_button = (
|
||||
(utils.get_space() is not None)
|
||||
if show_share_button is None
|
||||
else show_share_button
|
||||
)
|
||||
self.show_download_button = show_download_button
|
||||
self.min_length = min_length
|
||||
self.max_length = max_length
|
||||
self.streaming = streaming
|
||||
self.event_handler: Callable | None = None
|
||||
super().__init__(
|
||||
label=label,
|
||||
every=every,
|
||||
inputs=inputs,
|
||||
show_label=show_label,
|
||||
container=container,
|
||||
scale=scale,
|
||||
min_width=min_width,
|
||||
interactive=interactive,
|
||||
visible=visible,
|
||||
elem_id=elem_id,
|
||||
elem_classes=elem_classes,
|
||||
render=render,
|
||||
key=key,
|
||||
value=value,
|
||||
)
|
||||
|
||||
def preprocess(self, payload: str) -> str:
|
||||
"""
|
||||
Parameters:
|
||||
payload: An instance of VideoData containing the video and subtitle files.
|
||||
Returns:
|
||||
Passes the uploaded video as a `str` filepath or URL whose extension can be modified by `format`.
|
||||
"""
|
||||
return payload
|
||||
|
||||
|
||||
def postprocess(self, value: Any) -> str:
|
||||
"""
|
||||
Parameters:
|
||||
value: Expects a {str} or {pathlib.Path} filepath to a video which is displayed, or a {Tuple[str | pathlib.Path, str | pathlib.Path | None]} where the first element is a filepath to a video and the second element is an optional filepath to a subtitle file.
|
||||
Returns:
|
||||
VideoData object containing the video and subtitle files.
|
||||
"""
|
||||
return "__webrtc_value__"
|
||||
|
||||
def set_output(self, webrtc_id: str, *args):
|
||||
if webrtc_id in self.connections:
|
||||
self.connections[webrtc_id].latest_args = ["__webrtc_value__"] + list(args)
|
||||
|
||||
def webrtc_stream(
|
||||
self,
|
||||
fn: Callable[..., Any] | None = None,
|
||||
inputs: Block | Sequence[Block] | set[Block] | None = None,
|
||||
js: str | None = None,
|
||||
concurrency_limit: int | None | Literal["default"] = "default",
|
||||
concurrency_id: str | None = None,
|
||||
stream_every: float = 0.5,
|
||||
time_limit: float | None = None):
|
||||
|
||||
if inputs[0] != self:
|
||||
raise ValueError("In the webrtc_stream event, the first input component must be the WebRTC component.")
|
||||
|
||||
self.concurrency_limit = 1 if concurrency_limit in ["default", None] else concurrency_limit
|
||||
self.event_handler = fn
|
||||
return self.tick(self.set_output,
|
||||
inputs=inputs,
|
||||
outputs=None,
|
||||
concurrency_id=concurrency_id,
|
||||
concurrency_limit=None,
|
||||
stream_every=stream_every,
|
||||
time_limit=None,
|
||||
js=js
|
||||
)
|
||||
|
||||
@server
|
||||
async def offer(self, body):
|
||||
|
||||
if len(self.connections) >= self.concurrency_limit:
|
||||
return {"status": "failed"}
|
||||
|
||||
|
||||
offer = RTCSessionDescription(sdp=body['sdp'], type=body['type'])
|
||||
|
||||
pc = RTCPeerConnection()
|
||||
self.pcs.add(pc)
|
||||
|
||||
@pc.on("iceconnectionstatechange")
|
||||
async def on_iceconnectionstatechange():
|
||||
print(pc.iceConnectionState)
|
||||
if pc.iceConnectionState == "failed":
|
||||
await pc.close()
|
||||
self.pcs.discard(pc)
|
||||
|
||||
@pc.on("connectionstatechange")
|
||||
async def on_connectionstatechange():
|
||||
if pc.connectionState in ["failed", "closed"]:
|
||||
await pc.close()
|
||||
self.connections.pop(body['webrtc_id'], None)
|
||||
self.pcs.discard(pc)
|
||||
|
||||
@pc.on("track")
|
||||
def on_track(track):
|
||||
cb = VideoCallback(
|
||||
self.relay.subscribe(track),
|
||||
event_handler=cast(Callable, self.event_handler)
|
||||
)
|
||||
self.connections[body['webrtc_id']] = cb
|
||||
pc.addTrack(cb)
|
||||
|
||||
# handle offer
|
||||
await pc.setRemoteDescription(offer)
|
||||
|
||||
# send answer
|
||||
answer = await pc.createAnswer()
|
||||
await pc.setLocalDescription(answer) # type: ignore
|
||||
|
||||
return {
|
||||
"sdp": pc.localDescription.sdp,
|
||||
"type": pc.localDescription.type,
|
||||
}
|
||||
|
||||
def example_payload(self) -> Any:
|
||||
return {
|
||||
"video": handle_file(
|
||||
"https://github.com/gradio-app/gradio/raw/main/demo/video_component/files/world.mp4"
|
||||
),
|
||||
}
|
||||
|
||||
def example_value(self) -> Any:
|
||||
return "https://github.com/gradio-app/gradio/raw/main/demo/video_component/files/world.mp4"
|
||||
|
||||
|
||||
def api_info(self) -> Any:
|
||||
return {"type": "number"}
|
||||
|
||||
44
demo/README.md
Normal file
44
demo/README.md
Normal file
@@ -0,0 +1,44 @@
|
||||
---
|
||||
license: mit
|
||||
tags:
|
||||
- object-detection
|
||||
- computer-vision
|
||||
- yolov10
|
||||
datasets:
|
||||
- detection-datasets/coco
|
||||
sdk: gradio
|
||||
sdk_version: 5.0.0b1
|
||||
---
|
||||
|
||||
### Model Description
|
||||
[YOLOv10: Real-Time End-to-End Object Detection](https://arxiv.org/abs/2405.14458v1)
|
||||
|
||||
- arXiv: https://arxiv.org/abs/2405.14458v1
|
||||
- github: https://github.com/THU-MIG/yolov10
|
||||
|
||||
### Installation
|
||||
```
|
||||
pip install supervision git+https://github.com/THU-MIG/yolov10.git
|
||||
```
|
||||
|
||||
### Yolov10 Inference
|
||||
```python
|
||||
from ultralytics import YOLOv10
|
||||
import supervision as sv
|
||||
import cv2
|
||||
|
||||
IMAGE_PATH = 'dog.jpeg'
|
||||
|
||||
model = YOLOv10.from_pretrained('jameslahm/yolov10{n/s/m/b/l/x}')
|
||||
model.predict(IMAGE_PATH, show=True)
|
||||
```
|
||||
|
||||
### BibTeX Entry and Citation Info
|
||||
```
|
||||
@article{wang2024yolov10,
|
||||
title={YOLOv10: Real-Time End-to-End Object Detection},
|
||||
author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
|
||||
journal={arXiv preprint arXiv:2405.14458},
|
||||
year={2024}
|
||||
}
|
||||
```
|
||||
0
demo/__init__.py
Normal file
0
demo/__init__.py
Normal file
108
demo/app.py
Normal file
108
demo/app.py
Normal file
@@ -0,0 +1,108 @@
|
||||
import gradio as gr
|
||||
import cv2
|
||||
import numpy as np
|
||||
from gradio_webrtc import WebRTC
|
||||
from pathlib import Path
|
||||
|
||||
CLASSES = [
|
||||
"background",
|
||||
"aeroplane",
|
||||
"bicycle",
|
||||
"bird",
|
||||
"boat",
|
||||
"bottle",
|
||||
"bus",
|
||||
"car",
|
||||
"cat",
|
||||
"chair",
|
||||
"cow",
|
||||
"diningtable",
|
||||
"dog",
|
||||
"horse",
|
||||
"motorbike",
|
||||
"person",
|
||||
"pottedplant",
|
||||
"sheep",
|
||||
"sofa",
|
||||
"train",
|
||||
"tvmonitor",
|
||||
]
|
||||
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))
|
||||
|
||||
directory = Path(__file__).parent
|
||||
|
||||
MODEL = str((directory / "MobileNetSSD_deploy.caffemodel").resolve())
|
||||
PROTOTXT = str((directory / "MobileNetSSD_deploy.prototxt.txt").resolve())
|
||||
net = cv2.dnn.readNetFromCaffe(PROTOTXT, MODEL)
|
||||
|
||||
|
||||
def detection(image, conf_threshold=0.3):
|
||||
|
||||
blob = cv2.dnn.blobFromImage(
|
||||
cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5
|
||||
)
|
||||
net.setInput(blob)
|
||||
|
||||
detections = net.forward()
|
||||
image = cv2.resize(image, (500, 500))
|
||||
(h, w) = image.shape[:2]
|
||||
labels = []
|
||||
for i in np.arange(0, detections.shape[2]):
|
||||
confidence = detections[0, 0, i, 2]
|
||||
|
||||
if confidence > conf_threshold:
|
||||
# extract the index of the class label from the `detections`,
|
||||
# then compute the (x, y)-coordinates of the bounding box for
|
||||
# the object
|
||||
idx = int(detections[0, 0, i, 1])
|
||||
box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
|
||||
(startX, startY, endX, endY) = box.astype("int")
|
||||
|
||||
# display the prediction
|
||||
label = f"{CLASSES[idx]}: {round(confidence * 100, 2)}%"
|
||||
labels.append(label)
|
||||
cv2.rectangle(image, (startX, startY), (endX, endY), COLORS[idx], 2)
|
||||
y = startY - 15 if startY - 15 > 15 else startY + 15
|
||||
cv2.putText(
|
||||
image, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2
|
||||
)
|
||||
return image
|
||||
|
||||
|
||||
css=""".my-group {max-width: 600px !important; max-height: 600 !important;}
|
||||
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
|
||||
|
||||
|
||||
with gr.Blocks(css=css) as demo:
|
||||
gr.HTML(
|
||||
"""
|
||||
<h1 style='text-align: center'>
|
||||
YOLOv10 Webcam Stream
|
||||
</h1>
|
||||
""")
|
||||
gr.HTML(
|
||||
"""
|
||||
<h3 style='text-align: center'>
|
||||
<a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
|
||||
</h3>
|
||||
""")
|
||||
with gr.Column(elem_classes=["my-column"]):
|
||||
with gr.Group(elem_classes=["my-group"]):
|
||||
image = WebRTC(label="Strean")
|
||||
conf_threshold = gr.Slider(
|
||||
label="Confidence Threshold",
|
||||
minimum=0.0,
|
||||
maximum=1.0,
|
||||
step=0.05,
|
||||
value=0.30,
|
||||
)
|
||||
|
||||
image.webrtc_stream(
|
||||
fn=detection,
|
||||
inputs=[image],
|
||||
stream_every=0.05,
|
||||
time_limit=30
|
||||
)
|
||||
|
||||
if __name__ == '__main__':
|
||||
demo.launch()
|
||||
157
demo/css.css
Normal file
157
demo/css.css
Normal file
@@ -0,0 +1,157 @@
|
||||
html {
|
||||
font-family: Inter;
|
||||
font-size: 16px;
|
||||
font-weight: 400;
|
||||
line-height: 1.5;
|
||||
-webkit-text-size-adjust: 100%;
|
||||
background: #fff;
|
||||
color: #323232;
|
||||
-webkit-font-smoothing: antialiased;
|
||||
-moz-osx-font-smoothing: grayscale;
|
||||
text-rendering: optimizeLegibility;
|
||||
}
|
||||
|
||||
:root {
|
||||
--space: 1;
|
||||
--vspace: calc(var(--space) * 1rem);
|
||||
--vspace-0: calc(3 * var(--space) * 1rem);
|
||||
--vspace-1: calc(2 * var(--space) * 1rem);
|
||||
--vspace-2: calc(1.5 * var(--space) * 1rem);
|
||||
--vspace-3: calc(0.5 * var(--space) * 1rem);
|
||||
}
|
||||
|
||||
.app {
|
||||
max-width: 748px !important;
|
||||
}
|
||||
|
||||
.prose p {
|
||||
margin: var(--vspace) 0;
|
||||
line-height: var(--vspace * 2);
|
||||
font-size: 1rem;
|
||||
}
|
||||
|
||||
code {
|
||||
font-family: "Inconsolata", sans-serif;
|
||||
font-size: 16px;
|
||||
}
|
||||
|
||||
h1,
|
||||
h1 code {
|
||||
font-weight: 400;
|
||||
line-height: calc(2.5 / var(--space) * var(--vspace));
|
||||
}
|
||||
|
||||
h1 code {
|
||||
background: none;
|
||||
border: none;
|
||||
letter-spacing: 0.05em;
|
||||
padding-bottom: 5px;
|
||||
position: relative;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
h2 {
|
||||
margin: var(--vspace-1) 0 var(--vspace-2) 0;
|
||||
line-height: 1em;
|
||||
}
|
||||
|
||||
h3,
|
||||
h3 code {
|
||||
margin: var(--vspace-1) 0 var(--vspace-2) 0;
|
||||
line-height: 1em;
|
||||
}
|
||||
|
||||
h4,
|
||||
h5,
|
||||
h6 {
|
||||
margin: var(--vspace-3) 0 var(--vspace-3) 0;
|
||||
line-height: var(--vspace);
|
||||
}
|
||||
|
||||
.bigtitle,
|
||||
h1,
|
||||
h1 code {
|
||||
font-size: calc(8px * 4.5);
|
||||
word-break: break-word;
|
||||
}
|
||||
|
||||
.title,
|
||||
h2,
|
||||
h2 code {
|
||||
font-size: calc(8px * 3.375);
|
||||
font-weight: lighter;
|
||||
word-break: break-word;
|
||||
border: none;
|
||||
background: none;
|
||||
}
|
||||
|
||||
.subheading1,
|
||||
h3,
|
||||
h3 code {
|
||||
font-size: calc(8px * 1.8);
|
||||
font-weight: 600;
|
||||
border: none;
|
||||
background: none;
|
||||
letter-spacing: 0.1em;
|
||||
text-transform: uppercase;
|
||||
}
|
||||
|
||||
h2 code {
|
||||
padding: 0;
|
||||
position: relative;
|
||||
letter-spacing: 0.05em;
|
||||
}
|
||||
|
||||
blockquote {
|
||||
font-size: calc(8px * 1.1667);
|
||||
font-style: italic;
|
||||
line-height: calc(1.1667 * var(--vspace));
|
||||
margin: var(--vspace-2) var(--vspace-2);
|
||||
}
|
||||
|
||||
.subheading2,
|
||||
h4 {
|
||||
font-size: calc(8px * 1.4292);
|
||||
text-transform: uppercase;
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
.subheading3,
|
||||
h5 {
|
||||
font-size: calc(8px * 1.2917);
|
||||
line-height: calc(1.2917 * var(--vspace));
|
||||
|
||||
font-weight: lighter;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 0.15em;
|
||||
}
|
||||
|
||||
h6 {
|
||||
font-size: calc(8px * 1.1667);
|
||||
font-size: 1.1667em;
|
||||
font-weight: normal;
|
||||
font-style: italic;
|
||||
font-family: "le-monde-livre-classic-byol", serif !important;
|
||||
letter-spacing: 0px !important;
|
||||
}
|
||||
|
||||
#start .md > *:first-child {
|
||||
margin-top: 0;
|
||||
}
|
||||
|
||||
h2 + h3 {
|
||||
margin-top: 0;
|
||||
}
|
||||
|
||||
.md hr {
|
||||
border: none;
|
||||
border-top: 1px solid var(--block-border-color);
|
||||
margin: var(--vspace-2) 0 var(--vspace-2) 0;
|
||||
}
|
||||
.prose ul {
|
||||
margin: var(--vspace-2) 0 var(--vspace-1) 0;
|
||||
}
|
||||
|
||||
.gap {
|
||||
gap: 0;
|
||||
}
|
||||
45
demo/draw_boxes.py
Normal file
45
demo/draw_boxes.py
Normal file
@@ -0,0 +1,45 @@
|
||||
from PIL import ImageDraw, ImageFont # type: ignore
|
||||
import colorsys
|
||||
|
||||
|
||||
def get_color(label):
|
||||
# Simple hash function to generate consistent colors for each label
|
||||
hash_value = hash(label)
|
||||
hue = (hash_value % 100) / 100.0
|
||||
saturation = 0.7
|
||||
value = 0.9
|
||||
rgb = colorsys.hsv_to_rgb(hue, saturation, value)
|
||||
return tuple(int(x * 255) for x in rgb)
|
||||
|
||||
|
||||
def draw_bounding_boxes(image, results: dict, model, threshold=0.3):
|
||||
draw = ImageDraw.Draw(image)
|
||||
font = ImageFont.load_default()
|
||||
|
||||
for score, label_id, box in zip(
|
||||
results["scores"], results["labels"], results["boxes"]
|
||||
):
|
||||
if score > threshold:
|
||||
label = model.config.id2label[label_id.item()]
|
||||
box = [round(i, 2) for i in box.tolist()]
|
||||
color = get_color(label)
|
||||
|
||||
# Draw bounding box
|
||||
draw.rectangle(box, outline=color, width=3) # type: ignore
|
||||
|
||||
# Prepare text
|
||||
text = f"{label}: {score:.2f}"
|
||||
text_bbox = draw.textbbox((0, 0), text, font=font)
|
||||
text_width = text_bbox[2] - text_bbox[0]
|
||||
text_height = text_bbox[3] - text_bbox[1]
|
||||
|
||||
# Draw text background
|
||||
draw.rectangle(
|
||||
[box[0], box[1] - text_height - 4, box[0] + text_width, box[1]], # type: ignore
|
||||
fill=color, # type: ignore
|
||||
)
|
||||
|
||||
# Draw text
|
||||
draw.text((box[0], box[1] - text_height - 4), text, fill="white", font=font)
|
||||
|
||||
return image
|
||||
3
demo/requirements.txt
Normal file
3
demo/requirements.txt
Normal file
@@ -0,0 +1,3 @@
|
||||
safetensors==0.4.3
|
||||
opencv-python
|
||||
https://gradio-builds.s3.amazonaws.com/5.0-dev/e85cc9248cc33e187528f24f3b4415ca7b9e7134/take2/gradio-5.0.0b1-py3-none-any.whl
|
||||
230
demo/space.py
Normal file
230
demo/space.py
Normal file
File diff suppressed because one or more lines are too long
78
frontend/Example.svelte
Normal file
78
frontend/Example.svelte
Normal file
@@ -0,0 +1,78 @@
|
||||
<script lang="ts">
|
||||
import Video from "./shared/Video.svelte";
|
||||
import { playable } from "./shared/utils";
|
||||
import { type FileData } from "@gradio/client";
|
||||
|
||||
export let type: "gallery" | "table";
|
||||
export let selected = false;
|
||||
export let value: { video: FileData; subtitles: FileData | null } | null;
|
||||
export let loop: boolean;
|
||||
let video: HTMLVideoElement;
|
||||
|
||||
async function init(): Promise<void> {
|
||||
video.muted = true;
|
||||
video.playsInline = true;
|
||||
video.controls = false;
|
||||
video.setAttribute("muted", "");
|
||||
|
||||
await video.play();
|
||||
video.pause();
|
||||
}
|
||||
</script>
|
||||
|
||||
{#if value}
|
||||
{#if playable()}
|
||||
<div
|
||||
class="container"
|
||||
class:table={type === "table"}
|
||||
class:gallery={type === "gallery"}
|
||||
class:selected
|
||||
>
|
||||
<Video
|
||||
muted
|
||||
playsinline
|
||||
bind:node={video}
|
||||
on:loadeddata={init}
|
||||
on:mouseover={video.play.bind(video)}
|
||||
on:mouseout={video.pause.bind(video)}
|
||||
src={value?.video.url}
|
||||
is_stream={false}
|
||||
{loop}
|
||||
/>
|
||||
</div>
|
||||
{:else}
|
||||
<div>{value}</div>
|
||||
{/if}
|
||||
{/if}
|
||||
|
||||
<style>
|
||||
.container {
|
||||
flex: none;
|
||||
max-width: none;
|
||||
}
|
||||
.container :global(video) {
|
||||
width: var(--size-full);
|
||||
height: var(--size-full);
|
||||
object-fit: cover;
|
||||
}
|
||||
|
||||
.container:hover,
|
||||
.container.selected {
|
||||
border-color: var(--border-color-accent);
|
||||
}
|
||||
.container.table {
|
||||
margin: 0 auto;
|
||||
border: 2px solid var(--border-color-primary);
|
||||
border-radius: var(--radius-lg);
|
||||
overflow: hidden;
|
||||
width: var(--size-20);
|
||||
height: var(--size-20);
|
||||
object-fit: cover;
|
||||
}
|
||||
|
||||
.container.gallery {
|
||||
height: var(--size-20);
|
||||
max-height: var(--size-20);
|
||||
object-fit: cover;
|
||||
}
|
||||
</style>
|
||||
144
frontend/Index.svelte
Normal file
144
frontend/Index.svelte
Normal file
@@ -0,0 +1,144 @@
|
||||
<svelte:options accessors={true} />
|
||||
|
||||
<script lang="ts">
|
||||
import type { Gradio, ShareData } from "@gradio/utils";
|
||||
|
||||
import type { FileData } from "@gradio/client";
|
||||
import { Block, UploadText } from "@gradio/atoms";
|
||||
import Video from "./shared/InteractiveVideo.svelte";
|
||||
import { StatusTracker } from "@gradio/statustracker";
|
||||
import type { LoadingStatus } from "@gradio/statustracker";
|
||||
|
||||
export let elem_id = "";
|
||||
export let elem_classes: string[] = [];
|
||||
export let visible = true;
|
||||
export let value: string;
|
||||
|
||||
export let label: string;
|
||||
export let root: string;
|
||||
export let show_label: boolean;
|
||||
export let loading_status: LoadingStatus;
|
||||
export let height: number | undefined;
|
||||
export let width: number | undefined;
|
||||
export let server: {
|
||||
offer: (body: any) => Promise<any>;
|
||||
};
|
||||
|
||||
export let container = false;
|
||||
export let scale: number | null = null;
|
||||
export let min_width: number | undefined = undefined;
|
||||
export let gradio: Gradio<{
|
||||
change: never;
|
||||
clear: never;
|
||||
play: never;
|
||||
pause: never;
|
||||
upload: never;
|
||||
stop: never;
|
||||
end: never;
|
||||
start_recording: never;
|
||||
stop_recording: never;
|
||||
share: ShareData;
|
||||
error: string;
|
||||
warning: string;
|
||||
clear_status: LoadingStatus;
|
||||
tick: never;
|
||||
}>;
|
||||
export let mirror_webcam: boolean;
|
||||
export let include_audio: boolean;
|
||||
|
||||
let active_source: "webcam" | "upload";
|
||||
|
||||
let dragging = false;
|
||||
|
||||
$: console.log("value", value);
|
||||
|
||||
</script>
|
||||
|
||||
<!-- {#if !interactive}
|
||||
<Block
|
||||
{visible}
|
||||
variant={value === null && active_source === "upload" ? "dashed" : "solid"}
|
||||
border_mode={dragging ? "focus" : "base"}
|
||||
padding={false}
|
||||
{elem_id}
|
||||
{elem_classes}
|
||||
{height}
|
||||
{width}
|
||||
{container}
|
||||
{scale}
|
||||
{min_width}
|
||||
allow_overflow={false}
|
||||
>
|
||||
<StatusTracker
|
||||
autoscroll={gradio.autoscroll}
|
||||
i18n={gradio.i18n}
|
||||
{...loading_status}
|
||||
on:clear_status={() => gradio.dispatch("clear_status", loading_status)}
|
||||
/>
|
||||
|
||||
<StaticVideo
|
||||
value={_video}
|
||||
subtitle={_subtitle}
|
||||
{label}
|
||||
{show_label}
|
||||
{autoplay}
|
||||
{loop}
|
||||
{show_share_button}
|
||||
{show_download_button}
|
||||
on:play={() => gradio.dispatch("play")}
|
||||
on:pause={() => gradio.dispatch("pause")}
|
||||
on:stop={() => gradio.dispatch("stop")}
|
||||
on:end={() => gradio.dispatch("end")}
|
||||
on:share={({ detail }) => gradio.dispatch("share", detail)}
|
||||
on:error={({ detail }) => gradio.dispatch("error", detail)}
|
||||
i18n={gradio.i18n}
|
||||
upload={(...args) => gradio.client.upload(...args)}
|
||||
/>
|
||||
</Block>
|
||||
{:else} -->
|
||||
<Block
|
||||
{visible}
|
||||
variant={value === null && active_source === "upload" ? "dashed" : "solid"}
|
||||
border_mode={dragging ? "focus" : "base"}
|
||||
padding={false}
|
||||
{elem_id}
|
||||
{elem_classes}
|
||||
{height}
|
||||
{width}
|
||||
{container}
|
||||
{scale}
|
||||
{min_width}
|
||||
allow_overflow={false}
|
||||
>
|
||||
<StatusTracker
|
||||
autoscroll={gradio.autoscroll}
|
||||
i18n={gradio.i18n}
|
||||
{...loading_status}
|
||||
on:clear_status={() => gradio.dispatch("clear_status", loading_status)}
|
||||
/>
|
||||
|
||||
<Video
|
||||
bind:value={value}
|
||||
{label}
|
||||
{show_label}
|
||||
{active_source}
|
||||
{include_audio}
|
||||
{root}
|
||||
{server}
|
||||
on:clear={() => gradio.dispatch("clear")}
|
||||
on:play={() => gradio.dispatch("play")}
|
||||
on:pause={() => gradio.dispatch("pause")}
|
||||
on:upload={() => gradio.dispatch("upload")}
|
||||
on:stop={() => gradio.dispatch("stop")}
|
||||
on:end={() => gradio.dispatch("end")}
|
||||
on:start_recording={() => gradio.dispatch("start_recording")}
|
||||
on:stop_recording={() => gradio.dispatch("stop_recording")}
|
||||
on:tick={() => gradio.dispatch("tick")}
|
||||
on:error={({ detail }) => gradio.dispatch("error", detail)}
|
||||
i18n={gradio.i18n}
|
||||
stream_handler={(...args) => gradio.client.stream(...args)}
|
||||
>
|
||||
<UploadText i18n={gradio.i18n} type="video" />
|
||||
</Video>
|
||||
</Block>
|
||||
<!-- {/if} -->
|
||||
9
frontend/gradio.config.js
Normal file
9
frontend/gradio.config.js
Normal file
@@ -0,0 +1,9 @@
|
||||
export default {
|
||||
plugins: [],
|
||||
svelte: {
|
||||
preprocess: [],
|
||||
},
|
||||
build: {
|
||||
target: "modules",
|
||||
},
|
||||
};
|
||||
7
frontend/index.ts
Normal file
7
frontend/index.ts
Normal file
@@ -0,0 +1,7 @@
|
||||
export { default as BaseInteractiveVideo } from "./shared/InteractiveVideo.svelte";
|
||||
export { default as BaseStaticVideo } from "./shared/VideoPreview.svelte";
|
||||
export { default as BasePlayer } from "./shared/Player.svelte";
|
||||
export { prettyBytes, playable, loaded } from "./shared/utils";
|
||||
export { default as BaseExample } from "./Example.svelte";
|
||||
import { default as Index } from "./Index.svelte";
|
||||
export default Index;
|
||||
4963
frontend/package-lock.json
generated
Normal file
4963
frontend/package-lock.json
generated
Normal file
File diff suppressed because it is too large
Load Diff
59
frontend/package.json
Normal file
59
frontend/package.json
Normal file
@@ -0,0 +1,59 @@
|
||||
{
|
||||
"name": "gradio_webrtc",
|
||||
"version": "0.11.0-beta.3",
|
||||
"description": "Gradio UI packages",
|
||||
"type": "module",
|
||||
"author": "",
|
||||
"license": "ISC",
|
||||
"private": false,
|
||||
"dependencies": {
|
||||
"@ffmpeg/ffmpeg": "^0.12.7",
|
||||
"@ffmpeg/util": "^0.12.1",
|
||||
"@gradio/atoms": "0.9.0-beta.2",
|
||||
"@gradio/client": "1.6.0-beta.3",
|
||||
"@gradio/icons": "0.8.0-beta.2",
|
||||
"@gradio/image": "0.16.0-beta.3",
|
||||
"@gradio/statustracker": "0.8.0-beta.2",
|
||||
"@gradio/upload": "0.13.0-beta.3",
|
||||
"@gradio/utils": "0.7.0-beta.2",
|
||||
"@gradio/wasm": "0.14.0-beta.2",
|
||||
"hls.js": "^1.5.13",
|
||||
"mrmime": "^2.0.0"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@gradio/preview": "0.11.1"
|
||||
},
|
||||
"exports": {
|
||||
"./package.json": "./package.json",
|
||||
".": {
|
||||
"gradio": "./index.ts",
|
||||
"svelte": "./dist/index.js",
|
||||
"types": "./dist/index.d.ts"
|
||||
},
|
||||
"./example": {
|
||||
"gradio": "./Example.svelte",
|
||||
"svelte": "./dist/Example.svelte",
|
||||
"types": "./dist/Example.svelte.d.ts"
|
||||
},
|
||||
"./shared": {
|
||||
"gradio": "./shared/index.ts",
|
||||
"svelte": "./dist/shared/index.js",
|
||||
"types": "./dist/shared/index.d.ts"
|
||||
},
|
||||
"./base": {
|
||||
"gradio": "./shared/VideoPreview.svelte",
|
||||
"svelte": "./dist/shared/VideoPreview.svelte",
|
||||
"types": "./dist/shared/VideoPreview.svelte.d.ts"
|
||||
}
|
||||
},
|
||||
"peerDependencies": {
|
||||
"svelte": "^4.0.0"
|
||||
},
|
||||
"main": "index.ts",
|
||||
"main_changeset": true,
|
||||
"repository": {
|
||||
"type": "git",
|
||||
"url": "git+https://github.com/gradio-app/gradio.git",
|
||||
"directory": "js/video"
|
||||
}
|
||||
}
|
||||
87
frontend/shared/InteractiveVideo.svelte
Normal file
87
frontend/shared/InteractiveVideo.svelte
Normal file
@@ -0,0 +1,87 @@
|
||||
<script lang="ts">
|
||||
import { createEventDispatcher } from "svelte";
|
||||
import type { FileData, Client } from "@gradio/client";
|
||||
import { BlockLabel } from "@gradio/atoms";
|
||||
import Webcam from "./Webcam.svelte";
|
||||
import { Video } from "@gradio/icons";
|
||||
|
||||
import type { I18nFormatter } from "@gradio/utils";
|
||||
|
||||
export let value: string = null;
|
||||
export let label: string | undefined = undefined;
|
||||
export let show_label = true;
|
||||
export let include_audio: boolean;
|
||||
export let root: string;
|
||||
export let i18n: I18nFormatter;
|
||||
export let active_source: "webcam" | "upload" = "webcam";
|
||||
export let handle_reset_value: () => void = () => {};
|
||||
export let stream_handler: Client["stream"];
|
||||
export let server: {
|
||||
offer: (body: any) => Promise<any>;
|
||||
};
|
||||
|
||||
let has_change_history = false;
|
||||
|
||||
const dispatch = createEventDispatcher<{
|
||||
change: FileData | null;
|
||||
clear?: never;
|
||||
play?: never;
|
||||
pause?: never;
|
||||
end?: never;
|
||||
drag: boolean;
|
||||
error: string;
|
||||
upload: FileData;
|
||||
start_recording?: never;
|
||||
stop_recording?: never;
|
||||
tick: never;
|
||||
}>();
|
||||
|
||||
let dragging = false;
|
||||
$: dispatch("drag", dragging);
|
||||
|
||||
$: console.log("interactive value", value);
|
||||
</script>
|
||||
|
||||
<BlockLabel {show_label} Icon={Video} label={label || "Video"} />
|
||||
<div data-testid="video" class="video-container">
|
||||
<Webcam
|
||||
{root}
|
||||
{include_audio}
|
||||
on:error
|
||||
on:start_recording
|
||||
on:stop_recording
|
||||
on:tick
|
||||
{i18n}
|
||||
stream_every={0.5}
|
||||
{server}
|
||||
bind:webrtc_id={value}
|
||||
/>
|
||||
|
||||
<!-- <SelectSource {sources} bind:active_source /> -->
|
||||
</div>
|
||||
|
||||
<style>
|
||||
.file-name {
|
||||
padding: var(--size-6);
|
||||
font-size: var(--text-xxl);
|
||||
word-break: break-all;
|
||||
}
|
||||
|
||||
.file-size {
|
||||
padding: var(--size-2);
|
||||
font-size: var(--text-xl);
|
||||
}
|
||||
|
||||
.upload-container {
|
||||
height: 100%;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
.video-container {
|
||||
display: flex;
|
||||
height: 100%;
|
||||
flex-direction: column;
|
||||
justify-content: center;
|
||||
align-items: center;
|
||||
}
|
||||
</style>
|
||||
270
frontend/shared/Player.svelte
Normal file
270
frontend/shared/Player.svelte
Normal file
@@ -0,0 +1,270 @@
|
||||
<script lang="ts">
|
||||
import { createEventDispatcher } from "svelte";
|
||||
import { Play, Pause, Maximise, Undo } from "@gradio/icons";
|
||||
import Video from "./Video.svelte";
|
||||
import VideoControls from "./VideoControls.svelte";
|
||||
import type { FileData, Client } from "@gradio/client";
|
||||
import { prepare_files } from "@gradio/client";
|
||||
import { format_time } from "@gradio/utils";
|
||||
import type { I18nFormatter } from "@gradio/utils";
|
||||
|
||||
export let root = "";
|
||||
export let src: string;
|
||||
export let subtitle: string | null = null;
|
||||
export let mirror: boolean;
|
||||
export let autoplay: boolean;
|
||||
export let loop: boolean;
|
||||
export let label = "test";
|
||||
export let interactive = false;
|
||||
export let handle_change: (video: FileData) => void = () => {};
|
||||
export let handle_reset_value: () => void = () => {};
|
||||
export let upload: Client["upload"];
|
||||
export let is_stream: boolean | undefined;
|
||||
export let i18n: I18nFormatter;
|
||||
export let show_download_button = false;
|
||||
export let value: FileData | null = null;
|
||||
export let handle_clear: () => void = () => {};
|
||||
export let has_change_history = false;
|
||||
|
||||
const dispatch = createEventDispatcher<{
|
||||
play: undefined;
|
||||
pause: undefined;
|
||||
stop: undefined;
|
||||
end: undefined;
|
||||
clear: undefined;
|
||||
}>();
|
||||
|
||||
let time = 0;
|
||||
let duration: number;
|
||||
let paused = true;
|
||||
let video: HTMLVideoElement;
|
||||
let processingVideo = false;
|
||||
|
||||
function handleMove(e: TouchEvent | MouseEvent): void {
|
||||
if (!duration) return;
|
||||
|
||||
if (e.type === "click") {
|
||||
handle_click(e as MouseEvent);
|
||||
return;
|
||||
}
|
||||
|
||||
if (e.type !== "touchmove" && !((e as MouseEvent).buttons & 1)) return;
|
||||
|
||||
const clientX =
|
||||
e.type === "touchmove"
|
||||
? (e as TouchEvent).touches[0].clientX
|
||||
: (e as MouseEvent).clientX;
|
||||
const { left, right } = (
|
||||
e.currentTarget as HTMLProgressElement
|
||||
).getBoundingClientRect();
|
||||
time = (duration * (clientX - left)) / (right - left);
|
||||
}
|
||||
|
||||
async function play_pause(): Promise<void> {
|
||||
if (document.fullscreenElement != video) {
|
||||
const isPlaying =
|
||||
video.currentTime > 0 &&
|
||||
!video.paused &&
|
||||
!video.ended &&
|
||||
video.readyState > video.HAVE_CURRENT_DATA;
|
||||
|
||||
if (!isPlaying) {
|
||||
await video.play();
|
||||
} else video.pause();
|
||||
}
|
||||
}
|
||||
|
||||
function handle_click(e: MouseEvent): void {
|
||||
const { left, right } = (
|
||||
e.currentTarget as HTMLProgressElement
|
||||
).getBoundingClientRect();
|
||||
time = (duration * (e.clientX - left)) / (right - left);
|
||||
}
|
||||
|
||||
function handle_end(): void {
|
||||
dispatch("stop");
|
||||
dispatch("end");
|
||||
}
|
||||
|
||||
const handle_trim_video = async (videoBlob: Blob): Promise<void> => {
|
||||
let _video_blob = new File([videoBlob], "video.mp4");
|
||||
const val = await prepare_files([_video_blob]);
|
||||
let value = ((await upload(val, root))?.filter(Boolean) as FileData[])[0];
|
||||
|
||||
handle_change(value);
|
||||
};
|
||||
|
||||
function open_full_screen(): void {
|
||||
video.requestFullscreen();
|
||||
}
|
||||
</script>
|
||||
|
||||
<div class="wrap">
|
||||
<div class="mirror-wrap" class:mirror>
|
||||
<Video
|
||||
{src}
|
||||
preload="auto"
|
||||
{autoplay}
|
||||
{loop}
|
||||
{is_stream}
|
||||
on:click={play_pause}
|
||||
on:play
|
||||
on:pause
|
||||
on:ended={handle_end}
|
||||
bind:currentTime={time}
|
||||
bind:duration
|
||||
bind:paused
|
||||
bind:node={video}
|
||||
data-testid={`${label}-player`}
|
||||
{processingVideo}
|
||||
on:load
|
||||
>
|
||||
<track kind="captions" src={subtitle} default />
|
||||
</Video>
|
||||
</div>
|
||||
|
||||
<div class="controls">
|
||||
<div class="inner">
|
||||
<span
|
||||
role="button"
|
||||
tabindex="0"
|
||||
class="icon"
|
||||
aria-label="play-pause-replay-button"
|
||||
on:click={play_pause}
|
||||
on:keydown={play_pause}
|
||||
>
|
||||
{#if time === duration}
|
||||
<Undo />
|
||||
{:else if paused}
|
||||
<Play />
|
||||
{:else}
|
||||
<Pause />
|
||||
{/if}
|
||||
</span>
|
||||
|
||||
<span class="time">{format_time(time)} / {format_time(duration)}</span>
|
||||
|
||||
<!-- TODO: implement accessible video timeline for 4.0 -->
|
||||
<!-- svelte-ignore a11y-click-events-have-key-events -->
|
||||
<!-- svelte-ignore a11y-no-noninteractive-element-interactions -->
|
||||
<progress
|
||||
value={time / duration || 0}
|
||||
on:mousemove={handleMove}
|
||||
on:touchmove|preventDefault={handleMove}
|
||||
on:click|stopPropagation|preventDefault={handle_click}
|
||||
/>
|
||||
|
||||
<div
|
||||
role="button"
|
||||
tabindex="0"
|
||||
class="icon"
|
||||
aria-label="full-screen"
|
||||
on:click={open_full_screen}
|
||||
on:keypress={open_full_screen}
|
||||
>
|
||||
<Maximise />
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
{#if interactive}
|
||||
<VideoControls
|
||||
videoElement={video}
|
||||
showRedo
|
||||
{handle_trim_video}
|
||||
{handle_reset_value}
|
||||
bind:processingVideo
|
||||
{value}
|
||||
{i18n}
|
||||
{show_download_button}
|
||||
{handle_clear}
|
||||
{has_change_history}
|
||||
/>
|
||||
{/if}
|
||||
|
||||
<style lang="postcss">
|
||||
span {
|
||||
text-shadow: 0 0 8px rgba(0, 0, 0, 0.5);
|
||||
}
|
||||
|
||||
progress {
|
||||
margin-right: var(--size-3);
|
||||
border-radius: var(--radius-sm);
|
||||
width: var(--size-full);
|
||||
height: var(--size-2);
|
||||
}
|
||||
|
||||
progress::-webkit-progress-bar {
|
||||
border-radius: 2px;
|
||||
background-color: rgba(255, 255, 255, 0.2);
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
progress::-webkit-progress-value {
|
||||
background-color: rgba(255, 255, 255, 0.9);
|
||||
}
|
||||
|
||||
.mirror {
|
||||
transform: scaleX(-1);
|
||||
}
|
||||
|
||||
.mirror-wrap {
|
||||
position: relative;
|
||||
height: 100%;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
.controls {
|
||||
position: absolute;
|
||||
bottom: 0;
|
||||
opacity: 0;
|
||||
transition: 500ms;
|
||||
margin: var(--size-2);
|
||||
border-radius: var(--radius-md);
|
||||
background: var(--color-grey-800);
|
||||
padding: var(--size-2) var(--size-1);
|
||||
width: calc(100% - 0.375rem * 2);
|
||||
width: calc(100% - var(--size-2) * 2);
|
||||
}
|
||||
.wrap:hover .controls {
|
||||
opacity: 1;
|
||||
}
|
||||
|
||||
.inner {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
padding-right: var(--size-2);
|
||||
padding-left: var(--size-2);
|
||||
width: var(--size-full);
|
||||
height: var(--size-full);
|
||||
}
|
||||
|
||||
.icon {
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
cursor: pointer;
|
||||
width: var(--size-6);
|
||||
color: white;
|
||||
}
|
||||
|
||||
.time {
|
||||
flex-shrink: 0;
|
||||
margin-right: var(--size-3);
|
||||
margin-left: var(--size-3);
|
||||
color: white;
|
||||
font-size: var(--text-sm);
|
||||
font-family: var(--font-mono);
|
||||
}
|
||||
.wrap {
|
||||
position: relative;
|
||||
background-color: var(--background-fill-secondary);
|
||||
height: var(--size-full);
|
||||
width: var(--size-full);
|
||||
border-radius: var(--radius-xl);
|
||||
}
|
||||
.wrap :global(video) {
|
||||
height: var(--size-full);
|
||||
width: var(--size-full);
|
||||
}
|
||||
</style>
|
||||
197
frontend/shared/Video.svelte
Normal file
197
frontend/shared/Video.svelte
Normal file
@@ -0,0 +1,197 @@
|
||||
<script lang="ts">
|
||||
import type { HTMLVideoAttributes } from "svelte/elements";
|
||||
import { createEventDispatcher } from "svelte";
|
||||
import { loaded } from "./utils";
|
||||
|
||||
import { resolve_wasm_src } from "@gradio/wasm/svelte";
|
||||
|
||||
import Hls from "hls.js";
|
||||
|
||||
export let src: HTMLVideoAttributes["src"] = undefined;
|
||||
|
||||
export let muted: HTMLVideoAttributes["muted"] = undefined;
|
||||
export let playsinline: HTMLVideoAttributes["playsinline"] = undefined;
|
||||
export let preload: HTMLVideoAttributes["preload"] = undefined;
|
||||
export let autoplay: HTMLVideoAttributes["autoplay"] = undefined;
|
||||
export let controls: HTMLVideoAttributes["controls"] = undefined;
|
||||
|
||||
export let currentTime: number | undefined = undefined;
|
||||
export let duration: number | undefined = undefined;
|
||||
export let paused: boolean | undefined = undefined;
|
||||
|
||||
export let node: HTMLVideoElement | undefined = undefined;
|
||||
export let loop: boolean;
|
||||
export let is_stream;
|
||||
|
||||
export let processingVideo = false;
|
||||
|
||||
let resolved_src: typeof src;
|
||||
let stream_active = false;
|
||||
|
||||
// The `src` prop can be updated before the Promise from `resolve_wasm_src` is resolved.
|
||||
// In such a case, the resolved value for the old `src` has to be discarded,
|
||||
// This variable `latest_src` is used to pick up only the value resolved for the latest `src` prop.
|
||||
let latest_src: typeof src;
|
||||
$: {
|
||||
// In normal (non-Wasm) Gradio, the `<img>` element should be rendered with the passed `src` props immediately
|
||||
// without waiting for `resolve_wasm_src()` to resolve.
|
||||
// If it waits, a blank element is displayed until the async task finishes
|
||||
// and it leads to undesirable flickering.
|
||||
// So set `src` to `resolved_src` here.
|
||||
resolved_src = src;
|
||||
|
||||
latest_src = src;
|
||||
const resolving_src = src;
|
||||
resolve_wasm_src(resolving_src).then((s) => {
|
||||
if (latest_src === resolving_src) {
|
||||
resolved_src = s;
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
const dispatch = createEventDispatcher();
|
||||
|
||||
function load_stream(
|
||||
src: string | null | undefined,
|
||||
is_stream: boolean,
|
||||
node: HTMLVideoElement | undefined
|
||||
): void {
|
||||
if (!src || !is_stream) return;
|
||||
if (!node) return;
|
||||
if (Hls.isSupported() && !stream_active) {
|
||||
const hls = new Hls({
|
||||
maxBufferLength: 1, // 0.5 seconds (500 ms)
|
||||
maxMaxBufferLength: 1, // Maximum max buffer length in seconds
|
||||
lowLatencyMode: true // Enable low latency mode
|
||||
});
|
||||
hls.loadSource(src);
|
||||
hls.attachMedia(node);
|
||||
hls.on(Hls.Events.MANIFEST_PARSED, function () {
|
||||
(node as HTMLVideoElement).play();
|
||||
});
|
||||
hls.on(Hls.Events.ERROR, function (event, data) {
|
||||
console.error("HLS error:", event, data);
|
||||
if (data.fatal) {
|
||||
switch (data.type) {
|
||||
case Hls.ErrorTypes.NETWORK_ERROR:
|
||||
console.error(
|
||||
"Fatal network error encountered, trying to recover"
|
||||
);
|
||||
hls.startLoad();
|
||||
break;
|
||||
case Hls.ErrorTypes.MEDIA_ERROR:
|
||||
console.error("Fatal media error encountered, trying to recover");
|
||||
hls.recoverMediaError();
|
||||
break;
|
||||
default:
|
||||
console.error("Fatal error, cannot recover");
|
||||
hls.destroy();
|
||||
break;
|
||||
}
|
||||
}
|
||||
});
|
||||
stream_active = true;
|
||||
}
|
||||
}
|
||||
|
||||
$: src, (stream_active = false);
|
||||
|
||||
$: load_stream(src, is_stream, node);
|
||||
</script>
|
||||
|
||||
<!--
|
||||
The spread operator with `$$props` or `$$restProps` can't be used here
|
||||
to pass props from the parent component to the <video> element
|
||||
because of its unexpected behavior: https://github.com/sveltejs/svelte/issues/7404
|
||||
For example, if we add {...$$props} or {...$$restProps}, the boolean props aside it like `controls` will be compiled as string "true" or "false" on the actual DOM.
|
||||
Then, even when `controls` is false, the compiled DOM would be `<video controls="false">` which is equivalent to `<video controls>` since the string "false" is even truthy.
|
||||
-->
|
||||
<div class:hidden={!processingVideo} class="overlay">
|
||||
<span class="load-wrap">
|
||||
<span class="loader" />
|
||||
</span>
|
||||
</div>
|
||||
<video
|
||||
src={resolved_src}
|
||||
{muted}
|
||||
{playsinline}
|
||||
{preload}
|
||||
{autoplay}
|
||||
{controls}
|
||||
{loop}
|
||||
on:loadeddata={dispatch.bind(null, "loadeddata")}
|
||||
on:click={dispatch.bind(null, "click")}
|
||||
on:play={dispatch.bind(null, "play")}
|
||||
on:pause={dispatch.bind(null, "pause")}
|
||||
on:ended={dispatch.bind(null, "ended")}
|
||||
on:mouseover={dispatch.bind(null, "mouseover")}
|
||||
on:mouseout={dispatch.bind(null, "mouseout")}
|
||||
on:focus={dispatch.bind(null, "focus")}
|
||||
on:blur={dispatch.bind(null, "blur")}
|
||||
on:load
|
||||
bind:currentTime
|
||||
bind:duration
|
||||
bind:paused
|
||||
bind:this={node}
|
||||
use:loaded={{ autoplay: autoplay ?? false }}
|
||||
data-testid={$$props["data-testid"]}
|
||||
crossorigin="anonymous"
|
||||
>
|
||||
<slot />
|
||||
</video>
|
||||
|
||||
<style>
|
||||
.overlay {
|
||||
position: absolute;
|
||||
background-color: rgba(0, 0, 0, 0.4);
|
||||
width: 100%;
|
||||
height: 100%;
|
||||
}
|
||||
|
||||
.hidden {
|
||||
display: none;
|
||||
}
|
||||
|
||||
.load-wrap {
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
align-items: center;
|
||||
height: 100%;
|
||||
}
|
||||
|
||||
.loader {
|
||||
display: flex;
|
||||
position: relative;
|
||||
background-color: var(--border-color-accent-subdued);
|
||||
animation: shadowPulse 2s linear infinite;
|
||||
box-shadow:
|
||||
-24px 0 var(--border-color-accent-subdued),
|
||||
24px 0 var(--border-color-accent-subdued);
|
||||
margin: var(--spacing-md);
|
||||
border-radius: 50%;
|
||||
width: 10px;
|
||||
height: 10px;
|
||||
scale: 0.5;
|
||||
}
|
||||
|
||||
@keyframes shadowPulse {
|
||||
33% {
|
||||
box-shadow:
|
||||
-24px 0 var(--border-color-accent-subdued),
|
||||
24px 0 #fff;
|
||||
background: #fff;
|
||||
}
|
||||
66% {
|
||||
box-shadow:
|
||||
-24px 0 #fff,
|
||||
24px 0 #fff;
|
||||
background: var(--border-color-accent-subdued);
|
||||
}
|
||||
100% {
|
||||
box-shadow:
|
||||
-24px 0 #fff,
|
||||
24px 0 var(--border-color-accent-subdued);
|
||||
background: #fff;
|
||||
}
|
||||
}
|
||||
</style>
|
||||
202
frontend/shared/VideoControls.svelte
Normal file
202
frontend/shared/VideoControls.svelte
Normal file
@@ -0,0 +1,202 @@
|
||||
<script lang="ts">
|
||||
import { Undo, Trim, Clear } from "@gradio/icons";
|
||||
import VideoTimeline from "./VideoTimeline.svelte";
|
||||
import { trimVideo } from "./utils";
|
||||
import { FFmpeg } from "@ffmpeg/ffmpeg";
|
||||
import loadFfmpeg from "./utils";
|
||||
import { onMount } from "svelte";
|
||||
import { format_time } from "@gradio/utils";
|
||||
import { IconButton } from "@gradio/atoms";
|
||||
import { ModifyUpload } from "@gradio/upload";
|
||||
import type { FileData } from "@gradio/client";
|
||||
|
||||
export let videoElement: HTMLVideoElement;
|
||||
|
||||
export let showRedo = false;
|
||||
export let interactive = true;
|
||||
export let mode = "";
|
||||
export let handle_reset_value: () => void;
|
||||
export let handle_trim_video: (videoBlob: Blob) => void;
|
||||
export let processingVideo = false;
|
||||
export let i18n: (key: string) => string;
|
||||
export let value: FileData | null = null;
|
||||
export let show_download_button = false;
|
||||
export let handle_clear: () => void = () => {};
|
||||
export let has_change_history = false;
|
||||
|
||||
let ffmpeg: FFmpeg;
|
||||
|
||||
onMount(async () => {
|
||||
ffmpeg = await loadFfmpeg();
|
||||
});
|
||||
|
||||
$: if (mode === "edit" && trimmedDuration === null && videoElement)
|
||||
trimmedDuration = videoElement.duration;
|
||||
|
||||
let trimmedDuration: number | null = null;
|
||||
let dragStart = 0;
|
||||
let dragEnd = 0;
|
||||
|
||||
let loadingTimeline = false;
|
||||
|
||||
const toggleTrimmingMode = (): void => {
|
||||
if (mode === "edit") {
|
||||
mode = "";
|
||||
trimmedDuration = videoElement.duration;
|
||||
} else {
|
||||
mode = "edit";
|
||||
}
|
||||
};
|
||||
</script>
|
||||
|
||||
<div class="container" class:hidden={mode !== "edit"}>
|
||||
{#if mode === "edit"}
|
||||
<div class="timeline-wrapper">
|
||||
<VideoTimeline
|
||||
{videoElement}
|
||||
bind:dragStart
|
||||
bind:dragEnd
|
||||
bind:trimmedDuration
|
||||
bind:loadingTimeline
|
||||
/>
|
||||
</div>
|
||||
{/if}
|
||||
|
||||
<div class="controls" data-testid="waveform-controls">
|
||||
{#if mode === "edit" && trimmedDuration !== null}
|
||||
<time
|
||||
aria-label="duration of selected region in seconds"
|
||||
class:hidden={loadingTimeline}>{format_time(trimmedDuration)}</time
|
||||
>
|
||||
<div class="edit-buttons">
|
||||
<button
|
||||
class:hidden={loadingTimeline}
|
||||
class="text-button"
|
||||
on:click={() => {
|
||||
mode = "";
|
||||
processingVideo = true;
|
||||
trimVideo(ffmpeg, dragStart, dragEnd, videoElement)
|
||||
.then((videoBlob) => {
|
||||
handle_trim_video(videoBlob);
|
||||
})
|
||||
.then(() => {
|
||||
processingVideo = false;
|
||||
});
|
||||
}}>Trim</button
|
||||
>
|
||||
<button
|
||||
class="text-button"
|
||||
class:hidden={loadingTimeline}
|
||||
on:click={toggleTrimmingMode}>Cancel</button
|
||||
>
|
||||
</div>
|
||||
{:else}
|
||||
<div />
|
||||
{/if}
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<ModifyUpload
|
||||
{i18n}
|
||||
on:clear={() => handle_clear()}
|
||||
download={show_download_button ? value?.url : null}
|
||||
>
|
||||
{#if showRedo && mode === ""}
|
||||
<IconButton
|
||||
Icon={Undo}
|
||||
label="Reset video to initial value"
|
||||
disabled={processingVideo || !has_change_history}
|
||||
on:click={() => {
|
||||
handle_reset_value();
|
||||
mode = "";
|
||||
}}
|
||||
/>
|
||||
{/if}
|
||||
|
||||
{#if interactive && mode === ""}
|
||||
<IconButton
|
||||
Icon={Trim}
|
||||
label="Trim video to selection"
|
||||
disabled={processingVideo}
|
||||
on:click={toggleTrimmingMode}
|
||||
/>
|
||||
{/if}
|
||||
</ModifyUpload>
|
||||
|
||||
<style>
|
||||
.container {
|
||||
width: 100%;
|
||||
}
|
||||
time {
|
||||
color: var(--color-accent);
|
||||
font-weight: bold;
|
||||
padding-left: var(--spacing-xs);
|
||||
}
|
||||
|
||||
.timeline-wrapper {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
.text-button {
|
||||
border: 1px solid var(--neutral-400);
|
||||
border-radius: var(--radius-sm);
|
||||
font-weight: 300;
|
||||
font-size: var(--size-3);
|
||||
text-align: center;
|
||||
color: var(--neutral-400);
|
||||
height: var(--size-5);
|
||||
font-weight: bold;
|
||||
padding: 0 5px;
|
||||
margin-left: 5px;
|
||||
}
|
||||
|
||||
.text-button:hover,
|
||||
.text-button:focus {
|
||||
color: var(--color-accent);
|
||||
border-color: var(--color-accent);
|
||||
}
|
||||
|
||||
.controls {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
margin: var(--spacing-lg);
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.edit-buttons {
|
||||
display: flex;
|
||||
gap: var(--spacing-sm);
|
||||
}
|
||||
|
||||
@media (max-width: 320px) {
|
||||
.controls {
|
||||
flex-direction: column;
|
||||
align-items: flex-start;
|
||||
}
|
||||
|
||||
.edit-buttons {
|
||||
margin-top: var(--spacing-sm);
|
||||
}
|
||||
|
||||
.controls * {
|
||||
margin: var(--spacing-sm);
|
||||
}
|
||||
|
||||
.controls .text-button {
|
||||
margin-left: 0;
|
||||
}
|
||||
}
|
||||
|
||||
.container {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
.hidden {
|
||||
display: none;
|
||||
}
|
||||
</style>
|
||||
108
frontend/shared/VideoPreview.svelte
Normal file
108
frontend/shared/VideoPreview.svelte
Normal file
@@ -0,0 +1,108 @@
|
||||
<script lang="ts">
|
||||
import { createEventDispatcher, afterUpdate, tick } from "svelte";
|
||||
import {
|
||||
BlockLabel,
|
||||
Empty,
|
||||
IconButton,
|
||||
ShareButton,
|
||||
IconButtonWrapper
|
||||
} from "@gradio/atoms";
|
||||
import type { FileData, Client } from "@gradio/client";
|
||||
import { Video, Download } from "@gradio/icons";
|
||||
import { DownloadLink } from "@gradio/wasm/svelte";
|
||||
|
||||
import Player from "./Player.svelte";
|
||||
import type { I18nFormatter } from "js/core/src/gradio_helper";
|
||||
|
||||
export let value: FileData | null = null;
|
||||
export let subtitle: FileData | null = null;
|
||||
export let label: string | undefined = undefined;
|
||||
export let show_label = true;
|
||||
export let autoplay: boolean;
|
||||
export let show_share_button = true;
|
||||
export let show_download_button = true;
|
||||
export let loop: boolean;
|
||||
export let i18n: I18nFormatter;
|
||||
export let upload: Client["upload"];
|
||||
|
||||
let old_value: FileData | null = null;
|
||||
let old_subtitle: FileData | null = null;
|
||||
|
||||
const dispatch = createEventDispatcher<{
|
||||
change: FileData;
|
||||
play: undefined;
|
||||
pause: undefined;
|
||||
end: undefined;
|
||||
stop: undefined;
|
||||
}>();
|
||||
|
||||
$: value && dispatch("change", value);
|
||||
|
||||
afterUpdate(async () => {
|
||||
// needed to bust subtitle caching issues on Chrome
|
||||
if (
|
||||
value !== old_value &&
|
||||
subtitle !== old_subtitle &&
|
||||
old_subtitle !== null
|
||||
) {
|
||||
old_value = value;
|
||||
value = null;
|
||||
await tick();
|
||||
value = old_value;
|
||||
}
|
||||
old_value = value;
|
||||
old_subtitle = subtitle;
|
||||
});
|
||||
</script>
|
||||
|
||||
<BlockLabel {show_label} Icon={Video} label={label || "Video"} />
|
||||
{#if !value || value.url === undefined}
|
||||
<Empty unpadded_box={true} size="large"><Video /></Empty>
|
||||
{:else}
|
||||
{#key value.url}
|
||||
<Player
|
||||
src={value.url}
|
||||
subtitle={subtitle?.url}
|
||||
is_stream={value.is_stream}
|
||||
{autoplay}
|
||||
on:play
|
||||
on:pause
|
||||
on:stop
|
||||
on:end
|
||||
on:load
|
||||
mirror={false}
|
||||
{label}
|
||||
{loop}
|
||||
interactive={false}
|
||||
{upload}
|
||||
{i18n}
|
||||
/>
|
||||
{/key}
|
||||
<div data-testid="download-div">
|
||||
<IconButtonWrapper>
|
||||
{#if show_download_button}
|
||||
<DownloadLink
|
||||
href={value.is_stream
|
||||
? value.url?.replace("playlist.m3u8", "playlist-file")
|
||||
: value.url}
|
||||
download={value.orig_name || value.path}
|
||||
>
|
||||
<IconButton Icon={Download} label="Download" />
|
||||
</DownloadLink>
|
||||
{/if}
|
||||
{#if show_share_button}
|
||||
<ShareButton
|
||||
{i18n}
|
||||
on:error
|
||||
on:share
|
||||
{value}
|
||||
formatter={async (value) => {
|
||||
if (!value) return "";
|
||||
let url = await uploadToHuggingFace(value.data, "url");
|
||||
return url;
|
||||
}}
|
||||
/>
|
||||
{/if}
|
||||
</IconButtonWrapper>
|
||||
</div>
|
||||
{/if}
|
||||
279
frontend/shared/VideoTimeline.svelte
Normal file
279
frontend/shared/VideoTimeline.svelte
Normal file
@@ -0,0 +1,279 @@
|
||||
<script lang="ts">
|
||||
import { onMount, onDestroy } from "svelte";
|
||||
|
||||
export let videoElement: HTMLVideoElement;
|
||||
export let trimmedDuration: number | null;
|
||||
export let dragStart: number;
|
||||
export let dragEnd: number;
|
||||
export let loadingTimeline: boolean;
|
||||
|
||||
let thumbnails: string[] = [];
|
||||
let numberOfThumbnails = 10;
|
||||
let intervalId: ReturnType<typeof setInterval> | undefined;
|
||||
let videoDuration: number;
|
||||
|
||||
let leftHandlePosition = 0;
|
||||
let rightHandlePosition = 100;
|
||||
|
||||
let dragging: string | null = null;
|
||||
|
||||
const startDragging = (side: string | null): void => {
|
||||
dragging = side;
|
||||
};
|
||||
|
||||
$: loadingTimeline = thumbnails.length !== numberOfThumbnails;
|
||||
|
||||
const stopDragging = (): void => {
|
||||
dragging = null;
|
||||
};
|
||||
|
||||
const drag = (event: { clientX: number }, distance?: number): void => {
|
||||
if (dragging) {
|
||||
const timeline = document.getElementById("timeline");
|
||||
|
||||
if (!timeline) return;
|
||||
|
||||
const rect = timeline.getBoundingClientRect();
|
||||
let newPercentage = ((event.clientX - rect.left) / rect.width) * 100;
|
||||
|
||||
if (distance) {
|
||||
// Move handle based on arrow key press
|
||||
newPercentage =
|
||||
dragging === "left"
|
||||
? leftHandlePosition + distance
|
||||
: rightHandlePosition + distance;
|
||||
} else {
|
||||
// Move handle based on mouse drag
|
||||
newPercentage = ((event.clientX - rect.left) / rect.width) * 100;
|
||||
}
|
||||
|
||||
newPercentage = Math.max(0, Math.min(newPercentage, 100)); // Keep within 0 and 100
|
||||
|
||||
if (dragging === "left") {
|
||||
leftHandlePosition = Math.min(newPercentage, rightHandlePosition);
|
||||
|
||||
// Calculate the new time and set it for the videoElement
|
||||
const newTimeLeft = (leftHandlePosition / 100) * videoDuration;
|
||||
videoElement.currentTime = newTimeLeft;
|
||||
|
||||
dragStart = newTimeLeft;
|
||||
} else if (dragging === "right") {
|
||||
rightHandlePosition = Math.max(newPercentage, leftHandlePosition);
|
||||
|
||||
const newTimeRight = (rightHandlePosition / 100) * videoDuration;
|
||||
videoElement.currentTime = newTimeRight;
|
||||
|
||||
dragEnd = newTimeRight;
|
||||
}
|
||||
|
||||
const startTime = (leftHandlePosition / 100) * videoDuration;
|
||||
const endTime = (rightHandlePosition / 100) * videoDuration;
|
||||
trimmedDuration = endTime - startTime;
|
||||
|
||||
leftHandlePosition = leftHandlePosition;
|
||||
rightHandlePosition = rightHandlePosition;
|
||||
}
|
||||
};
|
||||
|
||||
const moveHandle = (e: KeyboardEvent): void => {
|
||||
if (dragging) {
|
||||
// Calculate the movement distance as a percentage of the video duration
|
||||
const distance = (1 / videoDuration) * 100;
|
||||
|
||||
if (e.key === "ArrowLeft") {
|
||||
drag({ clientX: 0 }, -distance);
|
||||
} else if (e.key === "ArrowRight") {
|
||||
drag({ clientX: 0 }, distance);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const generateThumbnail = (): void => {
|
||||
const canvas = document.createElement("canvas");
|
||||
const ctx = canvas.getContext("2d");
|
||||
if (!ctx) return;
|
||||
|
||||
canvas.width = videoElement.videoWidth;
|
||||
canvas.height = videoElement.videoHeight;
|
||||
|
||||
ctx.drawImage(videoElement, 0, 0, canvas.width, canvas.height);
|
||||
|
||||
const thumbnail: string = canvas.toDataURL("image/jpeg", 0.7);
|
||||
thumbnails = [...thumbnails, thumbnail];
|
||||
};
|
||||
|
||||
onMount(() => {
|
||||
const loadMetadata = (): void => {
|
||||
videoDuration = videoElement.duration;
|
||||
|
||||
const interval = videoDuration / numberOfThumbnails;
|
||||
let captures = 0;
|
||||
|
||||
const onSeeked = (): void => {
|
||||
generateThumbnail();
|
||||
captures++;
|
||||
|
||||
if (captures < numberOfThumbnails) {
|
||||
videoElement.currentTime += interval;
|
||||
} else {
|
||||
videoElement.removeEventListener("seeked", onSeeked);
|
||||
}
|
||||
};
|
||||
|
||||
videoElement.addEventListener("seeked", onSeeked);
|
||||
videoElement.currentTime = 0;
|
||||
};
|
||||
|
||||
if (videoElement.readyState >= 1) {
|
||||
loadMetadata();
|
||||
} else {
|
||||
videoElement.addEventListener("loadedmetadata", loadMetadata);
|
||||
}
|
||||
});
|
||||
|
||||
onDestroy(() => {
|
||||
window.removeEventListener("mousemove", drag);
|
||||
window.removeEventListener("mouseup", stopDragging);
|
||||
window.removeEventListener("keydown", moveHandle);
|
||||
|
||||
if (intervalId !== undefined) {
|
||||
clearInterval(intervalId);
|
||||
}
|
||||
});
|
||||
|
||||
onMount(() => {
|
||||
window.addEventListener("mousemove", drag);
|
||||
window.addEventListener("mouseup", stopDragging);
|
||||
window.addEventListener("keydown", moveHandle);
|
||||
});
|
||||
</script>
|
||||
|
||||
<div class="container">
|
||||
{#if loadingTimeline}
|
||||
<div class="load-wrap">
|
||||
<span aria-label="loading timeline" class="loader" />
|
||||
</div>
|
||||
{:else}
|
||||
<div id="timeline" class="thumbnail-wrapper">
|
||||
<button
|
||||
aria-label="start drag handle for trimming video"
|
||||
class="handle left"
|
||||
on:mousedown={() => startDragging("left")}
|
||||
on:blur={stopDragging}
|
||||
on:keydown={(e) => {
|
||||
if (e.key === "ArrowLeft" || e.key == "ArrowRight") {
|
||||
startDragging("left");
|
||||
}
|
||||
}}
|
||||
style="left: {leftHandlePosition}%;"
|
||||
/>
|
||||
|
||||
<div
|
||||
class="opaque-layer"
|
||||
style="left: {leftHandlePosition}%; right: {100 - rightHandlePosition}%"
|
||||
/>
|
||||
|
||||
{#each thumbnails as thumbnail, i (i)}
|
||||
<img src={thumbnail} alt={`frame-${i}`} draggable="false" />
|
||||
{/each}
|
||||
<button
|
||||
aria-label="end drag handle for trimming video"
|
||||
class="handle right"
|
||||
on:mousedown={() => startDragging("right")}
|
||||
on:blur={stopDragging}
|
||||
on:keydown={(e) => {
|
||||
if (e.key === "ArrowLeft" || e.key == "ArrowRight") {
|
||||
startDragging("right");
|
||||
}
|
||||
}}
|
||||
style="left: {rightHandlePosition}%;"
|
||||
/>
|
||||
</div>
|
||||
{/if}
|
||||
</div>
|
||||
|
||||
<style>
|
||||
.load-wrap {
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
align-items: center;
|
||||
height: 100%;
|
||||
}
|
||||
.loader {
|
||||
display: flex;
|
||||
position: relative;
|
||||
background-color: var(--border-color-accent-subdued);
|
||||
animation: shadowPulse 2s linear infinite;
|
||||
box-shadow:
|
||||
-24px 0 var(--border-color-accent-subdued),
|
||||
24px 0 var(--border-color-accent-subdued);
|
||||
margin: var(--spacing-md);
|
||||
border-radius: 50%;
|
||||
width: 10px;
|
||||
height: 10px;
|
||||
scale: 0.5;
|
||||
}
|
||||
|
||||
@keyframes shadowPulse {
|
||||
33% {
|
||||
box-shadow:
|
||||
-24px 0 var(--border-color-accent-subdued),
|
||||
24px 0 #fff;
|
||||
background: #fff;
|
||||
}
|
||||
66% {
|
||||
box-shadow:
|
||||
-24px 0 #fff,
|
||||
24px 0 #fff;
|
||||
background: var(--border-color-accent-subdued);
|
||||
}
|
||||
100% {
|
||||
box-shadow:
|
||||
-24px 0 #fff,
|
||||
24px 0 var(--border-color-accent-subdued);
|
||||
background: #fff;
|
||||
}
|
||||
}
|
||||
|
||||
.container {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
margin: var(--spacing-lg) var(--spacing-lg) 0 var(--spacing-lg);
|
||||
}
|
||||
|
||||
#timeline {
|
||||
display: flex;
|
||||
height: var(--size-10);
|
||||
flex: 1;
|
||||
position: relative;
|
||||
}
|
||||
|
||||
img {
|
||||
flex: 1 1 auto;
|
||||
min-width: 0;
|
||||
object-fit: cover;
|
||||
height: var(--size-12);
|
||||
border: 1px solid var(--block-border-color);
|
||||
user-select: none;
|
||||
z-index: 1;
|
||||
}
|
||||
|
||||
.handle {
|
||||
width: 3px;
|
||||
background-color: var(--color-accent);
|
||||
cursor: ew-resize;
|
||||
height: var(--size-12);
|
||||
z-index: 3;
|
||||
position: absolute;
|
||||
}
|
||||
|
||||
.opaque-layer {
|
||||
background-color: rgba(230, 103, 40, 0.25);
|
||||
border: 1px solid var(--color-accent);
|
||||
height: var(--size-12);
|
||||
position: absolute;
|
||||
z-index: 2;
|
||||
}
|
||||
</style>
|
||||
402
frontend/shared/Webcam.svelte
Normal file
402
frontend/shared/Webcam.svelte
Normal file
@@ -0,0 +1,402 @@
|
||||
<script lang="ts">
|
||||
import { createEventDispatcher, onMount } from "svelte";
|
||||
import {
|
||||
Circle,
|
||||
Square,
|
||||
DropdownArrow,
|
||||
Spinner
|
||||
} from "@gradio/icons";
|
||||
import type { I18nFormatter } from "@gradio/utils";
|
||||
import { StreamingBar } from "@gradio/statustracker";
|
||||
import WebcamPermissions from "./WebcamPermissions.svelte";
|
||||
import { fade } from "svelte/transition";
|
||||
import {
|
||||
get_devices,
|
||||
get_video_stream,
|
||||
set_available_devices
|
||||
} from "./stream_utils";
|
||||
|
||||
import { start, stop } from "./webrtc_utils";
|
||||
|
||||
let video_source: HTMLVideoElement;
|
||||
let available_video_devices: MediaDeviceInfo[] = [];
|
||||
let selected_device: MediaDeviceInfo | null = null;
|
||||
let time_limit: number | null = null;
|
||||
let stream_state: "open" | "waiting" | "closed" = "closed";
|
||||
export const webrtc_id = Math.random().toString(36).substring(2);
|
||||
|
||||
export const modify_stream: (state: "open" | "closed" | "waiting") => void = (
|
||||
state: "open" | "closed" | "waiting"
|
||||
) => {
|
||||
if (state === "closed") {
|
||||
time_limit = null;
|
||||
stream_state = "closed";
|
||||
} else if (state === "waiting") {
|
||||
stream_state = "waiting";
|
||||
} else {
|
||||
stream_state = "open";
|
||||
}
|
||||
};
|
||||
|
||||
export const set_time_limit = (time: number): void => {
|
||||
if (recording) time_limit = time;
|
||||
};
|
||||
|
||||
let canvas: HTMLCanvasElement;
|
||||
export let pending = false;
|
||||
export let root = "";
|
||||
export let stream_every = 1;
|
||||
export let server: {
|
||||
offer: (body: any) => Promise<any>;
|
||||
};
|
||||
|
||||
export let include_audio: boolean;
|
||||
export let i18n: I18nFormatter;
|
||||
|
||||
const dispatch = createEventDispatcher<{
|
||||
tick: undefined;
|
||||
error: string;
|
||||
start_recording: undefined;
|
||||
stop_recording: undefined;
|
||||
close_stream: undefined;
|
||||
}>();
|
||||
|
||||
onMount(() => (canvas = document.createElement("canvas")));
|
||||
|
||||
const handle_device_change = async (event: InputEvent): Promise<void> => {
|
||||
const target = event.target as HTMLInputElement;
|
||||
const device_id = target.value;
|
||||
|
||||
await get_video_stream(include_audio, video_source, device_id).then(
|
||||
async (local_stream) => {
|
||||
stream = local_stream;
|
||||
selected_device =
|
||||
available_video_devices.find(
|
||||
(device) => device.deviceId === device_id
|
||||
) || null;
|
||||
options_open = false;
|
||||
}
|
||||
);
|
||||
};
|
||||
|
||||
async function access_webcam(): Promise<void> {
|
||||
try {
|
||||
get_video_stream(include_audio, video_source)
|
||||
.then(async (local_stream) => {
|
||||
webcam_accessed = true;
|
||||
available_video_devices = await get_devices();
|
||||
stream = local_stream;
|
||||
})
|
||||
.then(() => set_available_devices(available_video_devices))
|
||||
.then((devices) => {
|
||||
available_video_devices = devices;
|
||||
|
||||
const used_devices = stream
|
||||
.getTracks()
|
||||
.map((track) => track.getSettings()?.deviceId)[0];
|
||||
|
||||
selected_device = used_devices
|
||||
? devices.find((device) => device.deviceId === used_devices) ||
|
||||
available_video_devices[0]
|
||||
: available_video_devices[0];
|
||||
});
|
||||
|
||||
if (!navigator.mediaDevices || !navigator.mediaDevices.getUserMedia) {
|
||||
dispatch("error", i18n("image.no_webcam_support"));
|
||||
}
|
||||
} catch (err) {
|
||||
if (err instanceof DOMException && err.name == "NotAllowedError") {
|
||||
dispatch("error", i18n("image.allow_webcam_access"));
|
||||
} else {
|
||||
throw err;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let recording = false;
|
||||
let stream: MediaStream;
|
||||
|
||||
let webcam_accessed = false;
|
||||
let pc: RTCPeerConnection;
|
||||
|
||||
async function start_webrtc(): Promise<void> {
|
||||
if (stream_state === 'closed') {
|
||||
pc = new RTCPeerConnection();
|
||||
pc.addEventListener("connectionstatechange",
|
||||
(event) => {
|
||||
switch(pc.connectionState) {
|
||||
case "connected":
|
||||
stream_state = "open"
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
}
|
||||
)
|
||||
stream_state = "waiting"
|
||||
start(stream, pc, video_source, server.offer, webrtc_id).then((connection) => {
|
||||
pc = connection;
|
||||
}).catch(() => {
|
||||
console.log("catching")
|
||||
stream_state = "closed";
|
||||
dispatch("error", "Too many concurrent users. Come back later!");
|
||||
});
|
||||
} else {
|
||||
stop(pc);
|
||||
stream_state = "closed";
|
||||
await access_webcam();
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
window.setInterval(() => {
|
||||
if (stream_state == "open") {
|
||||
console.log("dispatching tick");
|
||||
dispatch("tick");
|
||||
}
|
||||
}, stream_every * 1000);
|
||||
|
||||
let options_open = false;
|
||||
|
||||
export function click_outside(node: Node, cb: any): any {
|
||||
const handle_click = (event: MouseEvent): void => {
|
||||
if (
|
||||
node &&
|
||||
!node.contains(event.target as Node) &&
|
||||
!event.defaultPrevented
|
||||
) {
|
||||
cb(event);
|
||||
}
|
||||
};
|
||||
|
||||
document.addEventListener("click", handle_click, true);
|
||||
|
||||
return {
|
||||
destroy() {
|
||||
document.removeEventListener("click", handle_click, true);
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
function handle_click_outside(event: MouseEvent): void {
|
||||
event.preventDefault();
|
||||
event.stopPropagation();
|
||||
options_open = false;
|
||||
}
|
||||
</script>
|
||||
|
||||
<div class="wrap">
|
||||
<StreamingBar {time_limit} />
|
||||
<!-- svelte-ignore a11y-media-has-caption -->
|
||||
<!-- need to suppress for video streaming https://github.com/sveltejs/svelte/issues/5967 -->
|
||||
<video
|
||||
bind:this={video_source}
|
||||
class:hide={!webcam_accessed}
|
||||
class:flip={(stream_state != "open")}
|
||||
autoplay={true}
|
||||
playsinline={true}
|
||||
/>
|
||||
<!-- svelte-ignore a11y-missing-attribute -->
|
||||
{#if !webcam_accessed}
|
||||
<div
|
||||
in:fade={{ delay: 100, duration: 200 }}
|
||||
title="grant webcam access"
|
||||
style="height: 100%"
|
||||
>
|
||||
<WebcamPermissions on:click={async () => access_webcam()} />
|
||||
</div>
|
||||
{:else}
|
||||
<div class="button-wrap">
|
||||
<button
|
||||
on:click={start_webrtc}
|
||||
aria-label={"start stream"}
|
||||
>
|
||||
{#if stream_state === "waiting"}
|
||||
<div class="icon-with-text" style="width:var(--size-24);">
|
||||
<div class="icon color-primary" title="spinner">
|
||||
<Spinner />
|
||||
</div>
|
||||
{i18n("audio.waiting")}
|
||||
</div>
|
||||
{:else if stream_state === "open"}
|
||||
<div class="icon-with-text">
|
||||
<div class="icon color-primary" title="stop recording">
|
||||
<Square />
|
||||
</div>
|
||||
{i18n("audio.stop")}
|
||||
</div>
|
||||
{:else}
|
||||
<div class="icon-with-text">
|
||||
<div class="icon color-primary" title="start recording">
|
||||
<Circle />
|
||||
</div>
|
||||
{i18n("audio.record")}
|
||||
</div>
|
||||
{/if}
|
||||
</button>
|
||||
{#if !recording}
|
||||
<button
|
||||
class="icon"
|
||||
on:click={() => (options_open = true)}
|
||||
aria-label="select input source"
|
||||
>
|
||||
<DropdownArrow />
|
||||
</button>
|
||||
{/if}
|
||||
</div>
|
||||
{#if options_open && selected_device}
|
||||
<select
|
||||
class="select-wrap"
|
||||
aria-label="select source"
|
||||
use:click_outside={handle_click_outside}
|
||||
on:change={handle_device_change}
|
||||
>
|
||||
<button
|
||||
class="inset-icon"
|
||||
on:click|stopPropagation={() => (options_open = false)}
|
||||
>
|
||||
<DropdownArrow />
|
||||
</button>
|
||||
{#if available_video_devices.length === 0}
|
||||
<option value="">{i18n("common.no_devices")}</option>
|
||||
{:else}
|
||||
{#each available_video_devices as device}
|
||||
<option
|
||||
value={device.deviceId}
|
||||
selected={selected_device.deviceId === device.deviceId}
|
||||
>
|
||||
{device.label}
|
||||
</option>
|
||||
{/each}
|
||||
{/if}
|
||||
</select>
|
||||
{/if}
|
||||
{/if}
|
||||
</div>
|
||||
|
||||
<style>
|
||||
.wrap {
|
||||
position: relative;
|
||||
width: var(--size-full);
|
||||
height: var(--size-full);
|
||||
}
|
||||
|
||||
.hide {
|
||||
display: none;
|
||||
}
|
||||
|
||||
video {
|
||||
width: var(--size-full);
|
||||
height: var(--size-full);
|
||||
object-fit: cover;
|
||||
}
|
||||
|
||||
.button-wrap {
|
||||
position: absolute;
|
||||
background-color: var(--block-background-fill);
|
||||
border: 1px solid var(--border-color-primary);
|
||||
border-radius: var(--radius-xl);
|
||||
padding: var(--size-1-5);
|
||||
display: flex;
|
||||
bottom: var(--size-2);
|
||||
left: 50%;
|
||||
transform: translate(-50%, 0);
|
||||
box-shadow: var(--shadow-drop-lg);
|
||||
border-radius: var(--radius-xl);
|
||||
line-height: var(--size-3);
|
||||
color: var(--button-secondary-text-color);
|
||||
}
|
||||
|
||||
.icon-with-text {
|
||||
width: var(--size-20);
|
||||
align-items: center;
|
||||
margin: 0 var(--spacing-xl);
|
||||
display: flex;
|
||||
justify-content: space-evenly;
|
||||
}
|
||||
|
||||
@media (--screen-md) {
|
||||
button {
|
||||
bottom: var(--size-4);
|
||||
}
|
||||
}
|
||||
|
||||
@media (--screen-xl) {
|
||||
button {
|
||||
bottom: var(--size-8);
|
||||
}
|
||||
}
|
||||
|
||||
.icon {
|
||||
width: 18px;
|
||||
height: 18px;
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.color-primary {
|
||||
fill: var(--primary-600);
|
||||
stroke: var(--primary-600);
|
||||
color: var(--primary-600);
|
||||
}
|
||||
|
||||
.flip {
|
||||
transform: scaleX(-1);
|
||||
}
|
||||
|
||||
.select-wrap {
|
||||
-webkit-appearance: none;
|
||||
-moz-appearance: none;
|
||||
appearance: none;
|
||||
color: var(--button-secondary-text-color);
|
||||
background-color: transparent;
|
||||
width: 95%;
|
||||
font-size: var(--text-md);
|
||||
position: absolute;
|
||||
bottom: var(--size-2);
|
||||
background-color: var(--block-background-fill);
|
||||
box-shadow: var(--shadow-drop-lg);
|
||||
border-radius: var(--radius-xl);
|
||||
z-index: var(--layer-top);
|
||||
border: 1px solid var(--border-color-primary);
|
||||
text-align: left;
|
||||
line-height: var(--size-4);
|
||||
white-space: nowrap;
|
||||
text-overflow: ellipsis;
|
||||
left: 50%;
|
||||
transform: translate(-50%, 0);
|
||||
max-width: var(--size-52);
|
||||
}
|
||||
|
||||
.select-wrap > option {
|
||||
padding: 0.25rem 0.5rem;
|
||||
border-bottom: 1px solid var(--border-color-accent);
|
||||
padding-right: var(--size-8);
|
||||
text-overflow: ellipsis;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.select-wrap > option:hover {
|
||||
background-color: var(--color-accent);
|
||||
}
|
||||
|
||||
.select-wrap > option:last-child {
|
||||
border: none;
|
||||
}
|
||||
|
||||
.inset-icon {
|
||||
position: absolute;
|
||||
top: 5px;
|
||||
right: -6.5px;
|
||||
width: var(--size-10);
|
||||
height: var(--size-5);
|
||||
opacity: 0.8;
|
||||
}
|
||||
|
||||
@media (--screen-md) {
|
||||
.wrap {
|
||||
font-size: var(--text-lg);
|
||||
}
|
||||
}
|
||||
</style>
|
||||
46
frontend/shared/WebcamPermissions.svelte
Normal file
46
frontend/shared/WebcamPermissions.svelte
Normal file
@@ -0,0 +1,46 @@
|
||||
<script lang="ts">
|
||||
import { Webcam } from "@gradio/icons";
|
||||
import { createEventDispatcher } from "svelte";
|
||||
|
||||
const dispatch = createEventDispatcher<{
|
||||
click: undefined;
|
||||
}>();
|
||||
</script>
|
||||
|
||||
<button style:height="100%" on:click={() => dispatch("click")}>
|
||||
<div class="wrap">
|
||||
<span class="icon-wrap">
|
||||
<Webcam />
|
||||
</span>
|
||||
{"Click to Access Webcam"}
|
||||
</div>
|
||||
</button>
|
||||
|
||||
<style>
|
||||
button {
|
||||
cursor: pointer;
|
||||
width: var(--size-full);
|
||||
}
|
||||
|
||||
.wrap {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
justify-content: center;
|
||||
align-items: center;
|
||||
min-height: var(--size-60);
|
||||
color: var(--block-label-text-color);
|
||||
height: 100%;
|
||||
padding-top: var(--size-3);
|
||||
}
|
||||
|
||||
.icon-wrap {
|
||||
width: 30px;
|
||||
margin-bottom: var(--spacing-lg);
|
||||
}
|
||||
|
||||
@media (--screen-md) {
|
||||
.wrap {
|
||||
font-size: var(--text-lg);
|
||||
}
|
||||
}
|
||||
</style>
|
||||
1
frontend/shared/index.ts
Normal file
1
frontend/shared/index.ts
Normal file
@@ -0,0 +1 @@
|
||||
export { default as Video } from "./Video.svelte";
|
||||
49
frontend/shared/stream_utils.ts
Normal file
49
frontend/shared/stream_utils.ts
Normal file
@@ -0,0 +1,49 @@
|
||||
export function get_devices(): Promise<MediaDeviceInfo[]> {
|
||||
return navigator.mediaDevices.enumerateDevices();
|
||||
}
|
||||
|
||||
export function handle_error(error: string): void {
|
||||
throw new Error(error);
|
||||
}
|
||||
|
||||
export function set_local_stream(
|
||||
local_stream: MediaStream | null,
|
||||
video_source: HTMLVideoElement
|
||||
): void {
|
||||
video_source.srcObject = local_stream;
|
||||
video_source.muted = true;
|
||||
video_source.play();
|
||||
}
|
||||
|
||||
export async function get_video_stream(
|
||||
include_audio: boolean,
|
||||
video_source: HTMLVideoElement,
|
||||
device_id?: string
|
||||
): Promise<MediaStream> {
|
||||
const size = {
|
||||
width: { ideal: 1920 },
|
||||
height: { ideal: 1440 }
|
||||
};
|
||||
|
||||
const constraints = {
|
||||
video: device_id ? { deviceId: { exact: device_id }, ...size } : size,
|
||||
audio: include_audio
|
||||
};
|
||||
|
||||
return navigator.mediaDevices
|
||||
.getUserMedia(constraints)
|
||||
.then((local_stream: MediaStream) => {
|
||||
set_local_stream(local_stream, video_source);
|
||||
return local_stream;
|
||||
});
|
||||
}
|
||||
|
||||
export function set_available_devices(
|
||||
devices: MediaDeviceInfo[]
|
||||
): MediaDeviceInfo[] {
|
||||
const cameras = devices.filter(
|
||||
(device: MediaDeviceInfo) => device.kind === "videoinput"
|
||||
);
|
||||
|
||||
return cameras;
|
||||
}
|
||||
146
frontend/shared/utils.ts
Normal file
146
frontend/shared/utils.ts
Normal file
@@ -0,0 +1,146 @@
|
||||
import { toBlobURL } from "@ffmpeg/util";
|
||||
import { FFmpeg } from "@ffmpeg/ffmpeg";
|
||||
import { lookup } from "mrmime";
|
||||
|
||||
export const prettyBytes = (bytes: number): string => {
|
||||
let units = ["B", "KB", "MB", "GB", "PB"];
|
||||
let i = 0;
|
||||
while (bytes > 1024) {
|
||||
bytes /= 1024;
|
||||
i++;
|
||||
}
|
||||
let unit = units[i];
|
||||
return bytes.toFixed(1) + " " + unit;
|
||||
};
|
||||
|
||||
export const playable = (): boolean => {
|
||||
// TODO: Fix this
|
||||
// let video_element = document.createElement("video");
|
||||
// let mime_type = mime.lookup(filename);
|
||||
// return video_element.canPlayType(mime_type) != "";
|
||||
return true; // FIX BEFORE COMMIT - mime import causing issues
|
||||
};
|
||||
|
||||
export function loaded(
|
||||
node: HTMLVideoElement,
|
||||
{ autoplay }: { autoplay: boolean }
|
||||
): any {
|
||||
async function handle_playback(): Promise<void> {
|
||||
if (!autoplay) return;
|
||||
await node.play();
|
||||
}
|
||||
|
||||
node.addEventListener("loadeddata", handle_playback);
|
||||
|
||||
return {
|
||||
destroy(): void {
|
||||
node.removeEventListener("loadeddata", handle_playback);
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
export default async function loadFfmpeg(): Promise<FFmpeg> {
|
||||
const ffmpeg = new FFmpeg();
|
||||
const baseURL = "https://unpkg.com/@ffmpeg/core@0.12.4/dist/esm";
|
||||
|
||||
await ffmpeg.load({
|
||||
coreURL: await toBlobURL(`${baseURL}/ffmpeg-core.js`, "text/javascript"),
|
||||
wasmURL: await toBlobURL(`${baseURL}/ffmpeg-core.wasm`, "application/wasm")
|
||||
});
|
||||
|
||||
return ffmpeg;
|
||||
}
|
||||
|
||||
export function blob_to_data_url(blob: Blob): Promise<string> {
|
||||
return new Promise((fulfill, reject) => {
|
||||
let reader = new FileReader();
|
||||
reader.onerror = reject;
|
||||
reader.onload = () => fulfill(reader.result as string);
|
||||
reader.readAsDataURL(blob);
|
||||
});
|
||||
}
|
||||
|
||||
export async function trimVideo(
|
||||
ffmpeg: FFmpeg,
|
||||
startTime: number,
|
||||
endTime: number,
|
||||
videoElement: HTMLVideoElement
|
||||
): Promise<any> {
|
||||
const videoUrl = videoElement.src;
|
||||
const mimeType = lookup(videoElement.src) || "video/mp4";
|
||||
const blobUrl = await toBlobURL(videoUrl, mimeType);
|
||||
const response = await fetch(blobUrl);
|
||||
const vidBlob = await response.blob();
|
||||
const type = getVideoExtensionFromMimeType(mimeType) || "mp4";
|
||||
const inputName = `input.${type}`;
|
||||
const outputName = `output.${type}`;
|
||||
|
||||
try {
|
||||
if (startTime === 0 && endTime === 0) {
|
||||
return vidBlob;
|
||||
}
|
||||
|
||||
await ffmpeg.writeFile(
|
||||
inputName,
|
||||
new Uint8Array(await vidBlob.arrayBuffer())
|
||||
);
|
||||
|
||||
let command = [
|
||||
"-i",
|
||||
inputName,
|
||||
...(startTime !== 0 ? ["-ss", startTime.toString()] : []),
|
||||
...(endTime !== 0 ? ["-to", endTime.toString()] : []),
|
||||
"-c:a",
|
||||
"copy",
|
||||
outputName
|
||||
];
|
||||
|
||||
await ffmpeg.exec(command);
|
||||
const outputData = await ffmpeg.readFile(outputName);
|
||||
const outputBlob = new Blob([outputData], {
|
||||
type: `video/${type}`
|
||||
});
|
||||
|
||||
return outputBlob;
|
||||
} catch (error) {
|
||||
console.error("Error initializing FFmpeg:", error);
|
||||
return vidBlob;
|
||||
}
|
||||
}
|
||||
|
||||
const getVideoExtensionFromMimeType = (mimeType: string): string | null => {
|
||||
const videoMimeToExtensionMap: { [key: string]: string } = {
|
||||
"video/mp4": "mp4",
|
||||
"video/webm": "webm",
|
||||
"video/ogg": "ogv",
|
||||
"video/quicktime": "mov",
|
||||
"video/x-msvideo": "avi",
|
||||
"video/x-matroska": "mkv",
|
||||
"video/mpeg": "mpeg",
|
||||
"video/3gpp": "3gp",
|
||||
"video/3gpp2": "3g2",
|
||||
"video/h261": "h261",
|
||||
"video/h263": "h263",
|
||||
"video/h264": "h264",
|
||||
"video/jpeg": "jpgv",
|
||||
"video/jpm": "jpm",
|
||||
"video/mj2": "mj2",
|
||||
"video/mpv": "mpv",
|
||||
"video/vnd.ms-playready.media.pyv": "pyv",
|
||||
"video/vnd.uvvu.mp4": "uvu",
|
||||
"video/vnd.vivo": "viv",
|
||||
"video/x-f4v": "f4v",
|
||||
"video/x-fli": "fli",
|
||||
"video/x-flv": "flv",
|
||||
"video/x-m4v": "m4v",
|
||||
"video/x-ms-asf": "asf",
|
||||
"video/x-ms-wm": "wm",
|
||||
"video/x-ms-wmv": "wmv",
|
||||
"video/x-ms-wmx": "wmx",
|
||||
"video/x-ms-wvx": "wvx",
|
||||
"video/x-sgi-movie": "movie",
|
||||
"video/x-smv": "smv"
|
||||
};
|
||||
|
||||
return videoMimeToExtensionMap[mimeType] || null;
|
||||
};
|
||||
141
frontend/shared/webrtc_utils.ts
Normal file
141
frontend/shared/webrtc_utils.ts
Normal file
@@ -0,0 +1,141 @@
|
||||
export function createPeerConnection(pc, node) {
|
||||
// register some listeners to help debugging
|
||||
pc.addEventListener(
|
||||
"icegatheringstatechange",
|
||||
() => {
|
||||
console.log(pc.iceGatheringState);
|
||||
},
|
||||
false
|
||||
);
|
||||
|
||||
pc.addEventListener(
|
||||
"iceconnectionstatechange",
|
||||
() => {
|
||||
console.log(pc.iceConnectionState);
|
||||
},
|
||||
false
|
||||
);
|
||||
|
||||
pc.addEventListener(
|
||||
"signalingstatechange",
|
||||
() => {
|
||||
console.log(pc.signalingState);
|
||||
},
|
||||
false
|
||||
);
|
||||
|
||||
// connect audio / video from server to local
|
||||
pc.addEventListener("track", (evt) => {
|
||||
console.log("track event listener");
|
||||
if (evt.track.kind == "video") {
|
||||
console.log("streams", evt.streams);
|
||||
node.srcObject = evt.streams[0];
|
||||
console.log("node.srcOject", node.srcObject);
|
||||
}
|
||||
});
|
||||
|
||||
return pc;
|
||||
}
|
||||
|
||||
export async function start(stream, pc, node, server_fn, webrtc_id) {
|
||||
pc = createPeerConnection(pc, node);
|
||||
if (stream) {
|
||||
stream.getTracks().forEach((track) => {
|
||||
track.applyConstraints({ frameRate: { max: 30 } });
|
||||
|
||||
console.log("Track stream callback", track);
|
||||
pc.addTrack(track, stream);
|
||||
});
|
||||
} else {
|
||||
console.log("Creating transceiver!");
|
||||
pc.addTransceiver("video", { direction: "recvonly" });
|
||||
}
|
||||
|
||||
await negotiate(pc, server_fn, webrtc_id);
|
||||
return pc;
|
||||
}
|
||||
|
||||
function make_offer(server_fn: any, body): Promise<object> {
|
||||
return new Promise((resolve, reject) => {
|
||||
server_fn(body).then((data) => {
|
||||
console.log("data", data)
|
||||
if(data?.status === "failed") {
|
||||
console.log("rejecting")
|
||||
reject("error")
|
||||
}
|
||||
resolve(data);
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
async function negotiate(
|
||||
pc: RTCPeerConnection,
|
||||
server_fn: any,
|
||||
webrtc_id: string,
|
||||
): Promise<void> {
|
||||
return pc
|
||||
.createOffer()
|
||||
.then((offer) => {
|
||||
return pc.setLocalDescription(offer);
|
||||
})
|
||||
.then(() => {
|
||||
// wait for ICE gathering to complete
|
||||
return new Promise<void>((resolve) => {
|
||||
console.log("ice gathering state", pc.iceGatheringState);
|
||||
if (pc.iceGatheringState === "complete") {
|
||||
resolve();
|
||||
} else {
|
||||
const checkState = () => {
|
||||
if (pc.iceGatheringState === "complete") {
|
||||
console.log("ice complete");
|
||||
pc.removeEventListener("icegatheringstatechange", checkState);
|
||||
resolve();
|
||||
}
|
||||
};
|
||||
pc.addEventListener("icegatheringstatechange", checkState);
|
||||
}
|
||||
});
|
||||
})
|
||||
.then(() => {
|
||||
var offer = pc.localDescription;
|
||||
return make_offer(
|
||||
server_fn,
|
||||
{
|
||||
sdp: offer.sdp,
|
||||
type: offer.type,
|
||||
webrtc_id: webrtc_id
|
||||
},
|
||||
);
|
||||
})
|
||||
.then((response) => {
|
||||
return response;
|
||||
})
|
||||
.then((answer) => {
|
||||
return pc.setRemoteDescription(answer);
|
||||
})
|
||||
}
|
||||
|
||||
export function stop(pc: RTCPeerConnection) {
|
||||
console.log("pc", pc);
|
||||
console.log("STOPPING");
|
||||
// close transceivers
|
||||
if (pc.getTransceivers) {
|
||||
pc.getTransceivers().forEach((transceiver) => {
|
||||
if (transceiver.stop) {
|
||||
transceiver.stop();
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
// close local audio / video
|
||||
if (pc.getSenders()) {
|
||||
pc.getSenders().forEach((sender) => {
|
||||
if (sender.track && sender.track.stop) sender.track.stop();
|
||||
});
|
||||
}
|
||||
|
||||
// close peer connection
|
||||
setTimeout(() => {
|
||||
pc.close();
|
||||
}, 500);
|
||||
}
|
||||
51
pyproject.toml
Normal file
51
pyproject.toml
Normal file
@@ -0,0 +1,51 @@
|
||||
[build-system]
|
||||
requires = [
|
||||
"hatchling",
|
||||
"hatch-requirements-txt",
|
||||
"hatch-fancy-pypi-readme>=22.5.0",
|
||||
]
|
||||
build-backend = "hatchling.build"
|
||||
|
||||
[project]
|
||||
name = "gradio_webrtc"
|
||||
version = "0.0.1"
|
||||
description = "Stream images in realtime with webrtc"
|
||||
readme = "README.md"
|
||||
license = "apache-2.0"
|
||||
requires-python = ">=3.10"
|
||||
authors = [{ name = "YOUR NAME", email = "YOUREMAIL@domain.com" }]
|
||||
keywords = ["gradio-custom-component", "gradio-template-Video", "streaming", "webrtc", "realtime"]
|
||||
# Add dependencies here
|
||||
dependencies = ["gradio>=4.0,<5.0", "aiortc"]
|
||||
classifiers = [
|
||||
'Development Status :: 3 - Alpha',
|
||||
'Operating System :: OS Independent',
|
||||
'Programming Language :: Python :: 3',
|
||||
'Programming Language :: Python :: 3 :: Only',
|
||||
'Programming Language :: Python :: 3.8',
|
||||
'Programming Language :: Python :: 3.9',
|
||||
'Programming Language :: Python :: 3.10',
|
||||
'Programming Language :: Python :: 3.11',
|
||||
'Topic :: Scientific/Engineering',
|
||||
'Topic :: Scientific/Engineering :: Artificial Intelligence',
|
||||
'Topic :: Scientific/Engineering :: Visualization',
|
||||
]
|
||||
|
||||
# The repository and space URLs are optional, but recommended.
|
||||
# Adding a repository URL will create a badge in the auto-generated README that links to the repository.
|
||||
# Adding a space URL will create a badge in the auto-generated README that links to the space.
|
||||
# This will make it easy for people to find your deployed demo or source code when they
|
||||
# encounter your project in the wild.
|
||||
|
||||
# [project.urls]
|
||||
# repository = "your github repository"
|
||||
# space = "your space url"
|
||||
|
||||
[project.optional-dependencies]
|
||||
dev = ["build", "twine"]
|
||||
|
||||
[tool.hatch.build]
|
||||
artifacts = ["/backend/gradio_webrtc/templates", "*.pyi"]
|
||||
|
||||
[tool.hatch.build.targets.wheel]
|
||||
packages = ["/backend/gradio_webrtc"]
|
||||
Reference in New Issue
Block a user