deepgeek/gradio-webrtc
2
0
Fork 0
mirror of https://github.com/HumanAIGC-Engineering/gradio-webrtc.git synced 2026-02-05 18:09:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

t :# 请为您的变更输入提交说明。以 '#' 开始的行将被忽略，而一个空的提交

Browse Source
This commit is contained in:
杍超
2025-01-21 13:55:45 +08:00
commit 8a313bd700
62 changed files with 14687 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
demo/README.md Normal file
View 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
View File

105
demo/also_return_text.py Normal file
View File

@@ -0,0 +1,105 @@
import logging
import os
import gradio as gr
import numpy as np
from gradio_webrtc import AdditionalOutputs, WebRTC
from pydub import AudioSegment
from twilio.rest import Client
# Configure the root logger to WARNING to suppress debug messages from other libraries
logging.basicConfig(level=logging.WARNING)
# Create a console handler
console_handler = logging.FileHandler("gradio_webrtc.log")
console_handler.setLevel(logging.DEBUG)
# Create a formatter
formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
console_handler.setFormatter(formatter)
# Configure the logger for your specific library
logger = logging.getLogger("gradio_webrtc")
logger.setLevel(logging.DEBUG)
logger.addHandler(console_handler)
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation(num_steps):
for i in range(num_steps):
segment = AudioSegment.from_file(
"/Users/freddy/sources/gradio/demo/scratch/audio-streaming/librispeech.mp3"
)
yield (
(
segment.frame_rate,
np.array(segment.get_array_of_samples()).reshape(1, -1),
),
AdditionalOutputs(
f"Hello, from step {i}!",
"/Users/freddy/sources/gradio/demo/scratch/audio-streaming/librispeech.mp3",
),
)
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() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Audio Streaming (Powered by WebRTC ⚡️)
</h1>
"""
)
with gr.Column(elem_classes=["my-column"]):
with gr.Group(elem_classes=["my-group"]):
audio = WebRTC(
label="Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="audio",
)
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
textbox = gr.Textbox(placeholder="Output will appear here.")
audio_file = gr.Audio()
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio], trigger=button.click
)
audio.on_additional_outputs(
fn=lambda t, a: (f"State changed to {t}.", a),
outputs=[textbox, audio_file],
)
if __name__ == "__main__":
demo.launch(
allowed_paths=[
"/Users/freddy/sources/gradio/demo/scratch/audio-streaming/librispeech.mp3"
]
)

367
demo/app.py Normal file
View File

@@ -0,0 +1,367 @@
import os
import gradio as gr
_docs = {
"WebRTC": {
"description": "Stream audio/video with WebRTC",
"members": {
"__init__": {
"rtc_configuration": {
"type": "dict[str, Any] | None",
"default": "None",
"description": "The configration dictionary to pass to the RTCPeerConnection constructor. If None, the default configuration is used.",
},
"height": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "str | None",
"default": "None",
"description": "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.",
},
"show_label": {
"type": "bool | None",
"default": "None",
"description": "if True, will display label.",
},
"container": {
"type": "bool",
"default": "True",
"description": "if True, will place the component in a container - providing some extra padding around the border.",
},
"scale": {
"type": "int | None",
"default": "None",
"description": "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": {
"type": "int",
"default": "160",
"description": "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": {
"type": "bool | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "if False, component will be hidden.",
},
"elem_id": {
"type": "str | None",
"default": "None",
"description": "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": {
"type": "list[str] | str | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "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": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "if True webcam will be mirrored. Default is True.",
},
},
"events": {"tick": {"type": None, "default": None, "description": ""}},
},
"__meta__": {"additional_interfaces": {}, "user_fn_refs": {"WebRTC": []}},
}
}
abs_path = os.path.join(os.path.dirname(__file__), "css.css")
with gr.Blocks(
css_paths=abs_path,
theme=gr.themes.Default(
font_mono=[
gr.themes.GoogleFont("Inconsolata"),
"monospace",
],
),
) as demo:
gr.Markdown(
"""
<h1 style='text-align: center; margin-bottom: 1rem'> Gradio WebRTC ⚡️ </h1>
<div style="display: flex; flex-direction: row; justify-content: center">
<img style="display: block; padding-right: 5px; height: 20px;" alt="Static Badge" src="https://img.shields.io/badge/version%20-%200.0.6%20-%20orange">
<a href="https://github.com/freddyaboulton/gradio-webrtc" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/github-white?logo=github&logoColor=black"></a>
</div>
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
## Installation
```bash
pip install gradio_webrtc
```
## Examples:
1. [Object Detection from Webcam with YOLOv10](https://huggingface.co/spaces/freddyaboulton/webrtc-yolov10n) 📷
2. [Streaming Object Detection from Video with RT-DETR](https://huggingface.co/spaces/freddyaboulton/rt-detr-object-detection-webrtc) 🎥
3. [Text-to-Speech](https://huggingface.co/spaces/freddyaboulton/parler-tts-streaming-webrtc) 🗣️
4. [Conversational AI](https://huggingface.co/spaces/freddyaboulton/omni-mini-webrtc) 🤖🗣️
## Usage
The WebRTC component supports the following three use cases:
1. [Streaming video from the user webcam to the server and back](#h-streaming-video-from-the-user-webcam-to-the-server-and-back)
2. [Streaming Video from the server to the client](#h-streaming-video-from-the-server-to-the-client)
3. [Streaming Audio from the server to the client](#h-streaming-audio-from-the-server-to-the-client)
4. [Streaming Audio from the client to the server and back (conversational AI)](#h-conversational-ai)
## Streaming Video from the User Webcam to the Server and Back
```python
import gradio as gr
from gradio_webrtc import WebRTC
def detection(image, conf_threshold=0.3):
... your detection code here ...
with gr.Blocks() as demo:
image = WebRTC(label="Stream", mode="send-receive", modality="video")
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
image.stream(
fn=detection,
inputs=[image, conf_threshold],
outputs=[image], time_limit=10
)
if __name__ == "__main__":
demo.launch()
```
* Set the `mode` parameter to `send-receive` and `modality` to "video".
* The `stream` event's `fn` parameter is a function that receives the next frame from the webcam
as a **numpy array** and returns the processed frame also as a **numpy array**.
* Numpy arrays are in (height, width, 3) format where the color channels are in RGB format.
* The `inputs` parameter should be a list where the first element is the WebRTC component. The only output allowed is the WebRTC component.
* The `time_limit` parameter is the maximum time in seconds the video stream will run. If the time limit is reached, the video stream will stop.
## Streaming Video from the server to the client
```python
import gradio as gr
from gradio_webrtc import WebRTC
import cv2
def generation():
url = "https://download.tsi.telecom-paristech.fr/gpac/dataset/dash/uhd/mux_sources/hevcds_720p30_2M.mp4"
cap = cv2.VideoCapture(url)
iterating = True
while iterating:
iterating, frame = cap.read()
yield frame
with gr.Blocks() as demo:
output_video = WebRTC(label="Video Stream", mode="receive", modality="video")
button = gr.Button("Start", variant="primary")
output_video.stream(
fn=generation, inputs=None, outputs=[output_video],
trigger=button.click
)
if __name__ == "__main__":
demo.launch()
```
* Set the "mode" parameter to "receive" and "modality" to "video".
* The `stream` event's `fn` parameter is a generator function that yields the next frame from the video as a **numpy array**.
* The only output allowed is the WebRTC component.
* The `trigger` parameter the gradio event that will trigger the webrtc connection. In this case, the button click event.
## Streaming Audio from the Server to the Client
```python
import gradio as gr
from pydub import AudioSegment
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file("/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav")
yield (segment.frame_rate, np.array(segment.get_array_of_samples()).reshape(1, -1))
with gr.Blocks() as demo:
audio = WebRTC(label="Stream", mode="receive", modality="audio")
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio],
trigger=button.click
)
```
* Set the "mode" parameter to "receive" and "modality" to "audio".
* The `stream` event's `fn` parameter is a generator function that yields the next audio segment as a tuple of (frame_rate, audio_samples).
* The numpy array should be of shape (1, num_samples).
* The `outputs` parameter should be a list with the WebRTC component as the only element.
## Conversational AI
```python
import gradio as gr
import numpy as np
from gradio_webrtc import WebRTC, StreamHandler
from queue import Queue
import time
class EchoHandler(StreamHandler):
def __init__(self) -> None:
super().__init__()
self.queue = Queue()
def receive(self, frame: tuple[int, np.ndarray] | np.ndarray) -> None:
self.queue.put(frame)
def emit(self) -> None:
return self.queue.get()
with gr.Blocks() as demo:
with gr.Column():
with gr.Group():
audio = WebRTC(
label="Stream",
rtc_configuration=None,
mode="send-receive",
modality="audio",
)
audio.stream(fn=EchoHandler(), inputs=[audio], outputs=[audio], time_limit=15)
if __name__ == "__main__":
demo.launch()
```
* Instead of passing a function to the `stream` event's `fn` parameter, pass a `StreamHandler` implementation. The `StreamHandler` above simply echoes the audio back to the client.
* The `StreamHandler` class has two methods: `receive` and `emit`. The `receive` method is called when a new frame is received from the client, and the `emit` method returns the next frame to send to the client.
* An audio frame is represented as a tuple of (frame_rate, audio_samples) where `audio_samples` is a numpy array of shape (num_channels, num_samples).
* You can also specify the audio layout ("mono" or "stereo") in the emit method by retuning it as the third element of the tuple. If not specified, the default is "mono".
* The `time_limit` parameter is the maximum time in seconds the conversation will run. If the time limit is reached, the audio stream will stop.
* The `emit` method SHOULD NOT block. If a frame is not ready to be sent, the method should return None.
## Deployment
When deploying in a cloud environment (like Hugging Face Spaces, EC2, etc), you need to set up a TURN server to relay the WebRTC traffic.
The easiest way to do this is to use a service like Twilio.
```python
from twilio.rest import Client
import os
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
with gr.Blocks() as demo:
...
rtc = WebRTC(rtc_configuration=rtc_configuration, ...)
...
```
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
##
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.ParamViewer(value=_docs["WebRTC"]["members"]["__init__"], linkify=[])
demo.load(
None,
js=r"""function() {
const refs = {};
const user_fn_refs = {
WebRTC: [], };
requestAnimationFrame(() => {
Object.entries(user_fn_refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}-user-fn`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
Object.entries(refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
})
}
""",
)
demo.launch()

367
demo/app_.py Normal file
View File

@@ -0,0 +1,367 @@
import os
import gradio as gr
_docs = {
"WebRTC": {
"description": "Stream audio/video with WebRTC",
"members": {
"__init__": {
"rtc_configuration": {
"type": "dict[str, Any] | None",
"default": "None",
"description": "The configration dictionary to pass to the RTCPeerConnection constructor. If None, the default configuration is used.",
},
"height": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "str | None",
"default": "None",
"description": "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.",
},
"show_label": {
"type": "bool | None",
"default": "None",
"description": "if True, will display label.",
},
"container": {
"type": "bool",
"default": "True",
"description": "if True, will place the component in a container - providing some extra padding around the border.",
},
"scale": {
"type": "int | None",
"default": "None",
"description": "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": {
"type": "int",
"default": "160",
"description": "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": {
"type": "bool | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "if False, component will be hidden.",
},
"elem_id": {
"type": "str | None",
"default": "None",
"description": "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": {
"type": "list[str] | str | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "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": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "if True webcam will be mirrored. Default is True.",
},
},
"events": {"tick": {"type": None, "default": None, "description": ""}},
},
"__meta__": {"additional_interfaces": {}, "user_fn_refs": {"WebRTC": []}},
}
}
abs_path = os.path.join(os.path.dirname(__file__), "css.css")
with gr.Blocks(
css_paths=abs_path,
theme=gr.themes.Default(
font_mono=[
gr.themes.GoogleFont("Inconsolata"),
"monospace",
],
),
) as demo:
gr.Markdown(
"""
<h1 style='text-align: center; margin-bottom: 1rem'> Gradio WebRTC ⚡️ </h1>
<div style="display: flex; flex-direction: row; justify-content: center">
<img style="display: block; padding-right: 5px; height: 20px;" alt="Static Badge" src="https://img.shields.io/badge/version%20-%200.0.6%20-%20orange">
<a href="https://github.com/freddyaboulton/gradio-webrtc" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/github-white?logo=github&logoColor=black"></a>
</div>
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
## Installation
```bash
pip install gradio_webrtc
```
## Examples:
1. [Object Detection from Webcam with YOLOv10](https://huggingface.co/spaces/freddyaboulton/webrtc-yolov10n) 📷
2. [Streaming Object Detection from Video with RT-DETR](https://huggingface.co/spaces/freddyaboulton/rt-detr-object-detection-webrtc) 🎥
3. [Text-to-Speech](https://huggingface.co/spaces/freddyaboulton/parler-tts-streaming-webrtc) 🗣️
4. [Conversational AI](https://huggingface.co/spaces/freddyaboulton/omni-mini-webrtc) 🤖🗣️
## Usage
The WebRTC component supports the following three use cases:
1. [Streaming video from the user webcam to the server and back](#h-streaming-video-from-the-user-webcam-to-the-server-and-back)
2. [Streaming Video from the server to the client](#h-streaming-video-from-the-server-to-the-client)
3. [Streaming Audio from the server to the client](#h-streaming-audio-from-the-server-to-the-client)
4. [Streaming Audio from the client to the server and back (conversational AI)](#h-conversational-ai)
## Streaming Video from the User Webcam to the Server and Back
```python
import gradio as gr
from gradio_webrtc import WebRTC
def detection(image, conf_threshold=0.3):
... your detection code here ...
with gr.Blocks() as demo:
image = WebRTC(label="Stream", mode="send-receive", modality="video")
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
image.stream(
fn=detection,
inputs=[image, conf_threshold],
outputs=[image], time_limit=10
)
if __name__ == "__main__":
demo.launch()
```
* Set the `mode` parameter to `send-receive` and `modality` to "video".
* The `stream` event's `fn` parameter is a function that receives the next frame from the webcam
as a **numpy array** and returns the processed frame also as a **numpy array**.
* Numpy arrays are in (height, width, 3) format where the color channels are in RGB format.
* The `inputs` parameter should be a list where the first element is the WebRTC component. The only output allowed is the WebRTC component.
* The `time_limit` parameter is the maximum time in seconds the video stream will run. If the time limit is reached, the video stream will stop.
## Streaming Video from the server to the client
```python
import gradio as gr
from gradio_webrtc import WebRTC
import cv2
def generation():
url = "https://download.tsi.telecom-paristech.fr/gpac/dataset/dash/uhd/mux_sources/hevcds_720p30_2M.mp4"
cap = cv2.VideoCapture(url)
iterating = True
while iterating:
iterating, frame = cap.read()
yield frame
with gr.Blocks() as demo:
output_video = WebRTC(label="Video Stream", mode="receive", modality="video")
button = gr.Button("Start", variant="primary")
output_video.stream(
fn=generation, inputs=None, outputs=[output_video],
trigger=button.click
)
if __name__ == "__main__":
demo.launch()
```
* Set the "mode" parameter to "receive" and "modality" to "video".
* The `stream` event's `fn` parameter is a generator function that yields the next frame from the video as a **numpy array**.
* The only output allowed is the WebRTC component.
* The `trigger` parameter the gradio event that will trigger the webrtc connection. In this case, the button click event.
## Streaming Audio from the Server to the Client
```python
import gradio as gr
from pydub import AudioSegment
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file("/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav")
yield (segment.frame_rate, np.array(segment.get_array_of_samples()).reshape(1, -1))
with gr.Blocks() as demo:
audio = WebRTC(label="Stream", mode="receive", modality="audio")
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio],
trigger=button.click
)
```
* Set the "mode" parameter to "receive" and "modality" to "audio".
* The `stream` event's `fn` parameter is a generator function that yields the next audio segment as a tuple of (frame_rate, audio_samples).
* The numpy array should be of shape (1, num_samples).
* The `outputs` parameter should be a list with the WebRTC component as the only element.
## Conversational AI
```python
import gradio as gr
import numpy as np
from gradio_webrtc import WebRTC, StreamHandler
from queue import Queue
import time
class EchoHandler(StreamHandler):
def __init__(self) -> None:
super().__init__()
self.queue = Queue()
def receive(self, frame: tuple[int, np.ndarray] | np.ndarray) -> None:
self.queue.put(frame)
def emit(self) -> None:
return self.queue.get()
with gr.Blocks() as demo:
with gr.Column():
with gr.Group():
audio = WebRTC(
label="Stream",
rtc_configuration=None,
mode="send-receive",
modality="audio",
)
audio.stream(fn=EchoHandler(), inputs=[audio], outputs=[audio], time_limit=15)
if __name__ == "__main__":
demo.launch()
```
* Instead of passing a function to the `stream` event's `fn` parameter, pass a `StreamHandler` implementation. The `StreamHandler` above simply echoes the audio back to the client.
* The `StreamHandler` class has two methods: `receive` and `emit`. The `receive` method is called when a new frame is received from the client, and the `emit` method returns the next frame to send to the client.
* An audio frame is represented as a tuple of (frame_rate, audio_samples) where `audio_samples` is a numpy array of shape (num_channels, num_samples).
* You can also specify the audio layout ("mono" or "stereo") in the emit method by retuning it as the third element of the tuple. If not specified, the default is "mono".
* The `time_limit` parameter is the maximum time in seconds the conversation will run. If the time limit is reached, the audio stream will stop.
* The `emit` method SHOULD NOT block. If a frame is not ready to be sent, the method should return None.
## Deployment
When deploying in a cloud environment (like Hugging Face Spaces, EC2, etc), you need to set up a TURN server to relay the WebRTC traffic.
The easiest way to do this is to use a service like Twilio.
```python
from twilio.rest import Client
import os
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
with gr.Blocks() as demo:
...
rtc = WebRTC(rtc_configuration=rtc_configuration, ...)
...
```
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
##
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.ParamViewer(value=_docs["WebRTC"]["members"]["__init__"], linkify=[])
demo.load(
None,
js=r"""function() {
const refs = {};
const user_fn_refs = {
WebRTC: [], };
requestAnimationFrame(() => {
Object.entries(user_fn_refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}-user-fn`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
Object.entries(refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
})
}
""",
)
demo.launch()

73
demo/app_orig.py Normal file
View File

@@ -0,0 +1,73 @@
import os
import cv2
import gradio as gr
from gradio_webrtc import WebRTC
from huggingface_hub import hf_hub_download
from inference import YOLOv10
from twilio.rest import Client
model_file = hf_hub_download(
repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)
model = YOLOv10(model_file)
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def detection(image, conf_threshold=0.3):
image = cv2.resize(image, (model.input_width, model.input_height))
new_image = model.detect_objects(image, conf_threshold)
return cv2.resize(new_image, (500, 500))
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 (Powered by WebRTC ⚡️)
</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="Stream", rtc_configuration=rtc_configuration)
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
image.stream(
fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
)
if __name__ == "__main__":
demo.launch()

71
demo/audio_out.py Normal file
View File

@@ -0,0 +1,71 @@
import os
import gradio as gr
import numpy as np
from gradio_webrtc import WebRTC
from pydub import AudioSegment
from twilio.rest import Client
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file(
"/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav"
)
yield (
segment.frame_rate,
np.array(segment.get_array_of_samples()).reshape(1, -1),
)
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() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Audio Streaming (Powered by WebRTC ⚡️)
</h1>
"""
)
with gr.Column(elem_classes=["my-column"]):
with gr.Group(elem_classes=["my-group"]):
audio = WebRTC(
label="Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="audio",
)
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio], trigger=button.click
)
if __name__ == "__main__":
demo.launch()

64
demo/audio_out_2.py Normal file
View File

@@ -0,0 +1,64 @@
import os
import time
import gradio as gr
import numpy as np
from gradio_webrtc import WebRTC
from pydub import AudioSegment
from twilio.rest import Client
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file(
"/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav"
)
yield (
segment.frame_rate,
np.array(segment.get_array_of_samples()).reshape(1, -1),
)
time.sleep(3.5)
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() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Audio Streaming (Powered by WebRaTC ⚡️)
</h1>
"""
)
with gr.Row():
with gr.Column():
gr.Slider()
with gr.Column():
# audio = gr.Audio(interactive=False)
audio = WebRTC(
label="Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="audio",
)
if __name__ == "__main__":
demo.launch()

161
demo/css.css Normal file
View File

@@ -0,0 +1,161 @@
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;
}
.md-custom {
overflow: hidden;
}

99
demo/docs.py Normal file
View File

@@ -0,0 +1,99 @@
_docs = {
"WebRTC": {
"description": "Stream audio/video with WebRTC",
"members": {
"__init__": {
"rtc_configuration": {
"type": "dict[str, Any] | None",
"default": "None",
"description": "The configration dictionary to pass to the RTCPeerConnection constructor. If None, the default configuration is used.",
},
"height": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "str | None",
"default": "None",
"description": "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.",
},
"show_label": {
"type": "bool | None",
"default": "None",
"description": "if True, will display label.",
},
"container": {
"type": "bool",
"default": "True",
"description": "if True, will place the component in a container - providing some extra padding around the border.",
},
"scale": {
"type": "int | None",
"default": "None",
"description": "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": {
"type": "int",
"default": "160",
"description": "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": {
"type": "bool | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "if False, component will be hidden.",
},
"elem_id": {
"type": "str | None",
"default": "None",
"description": "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": {
"type": "list[str] | str | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "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": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "if True webcam will be mirrored. Default is True.",
},
"postprocess": {
"value": {
"type": "typing.Any",
"description": "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.",
}
},
"preprocess": {
"return": {
"type": "str",
"description": "Passes the uploaded video as a `str` filepath or URL whose extension can be modified by `format`.",
},
"value": None,
},
},
"events": {"tick": {"type": None, "default": None, "description": ""}},
},
"__meta__": {"additional_interfaces": {}, "user_fn_refs": {"WebRTC": []}},
}
}

61
demo/echo_conversation.py Normal file
View File

@@ -0,0 +1,61 @@
import logging
from queue import Queue
import gradio as gr
import numpy as np
from gradio_webrtc import StreamHandler, WebRTC
# Configure the root logger to WARNING to suppress debug messages from other libraries
logging.basicConfig(level=logging.WARNING)
# Create a console handler
console_handler = logging.StreamHandler()
console_handler.setLevel(logging.DEBUG)
# Create a formatter
formatter = logging.Formatter("%(name)s - %(levelname)s - %(message)s")
console_handler.setFormatter(formatter)
# Configure the logger for your specific library
logger = logging.getLogger("gradio_webrtc")
logger.setLevel(logging.DEBUG)
logger.addHandler(console_handler)
class EchoHandler(StreamHandler):
def __init__(self) -> None:
super().__init__()
self.queue = Queue()
def receive(self, frame: tuple[int, np.ndarray] | np.ndarray) -> None:
self.queue.put(frame)
def emit(self) -> None:
return self.queue.get()
def copy(self) -> StreamHandler:
return EchoHandler()
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Conversational AI (Powered by WebRTC ⚡️)
</h1>
"""
)
with gr.Column():
with gr.Group():
audio = WebRTC(
label="Stream",
rtc_configuration=None,
mode="send-receive",
modality="audio",
)
audio.stream(fn=EchoHandler(), inputs=[audio], outputs=[audio], time_limit=15)
if __name__ == "__main__":
demo.launch()

149
demo/inference.py Normal file
View File

@@ -0,0 +1,149 @@
import time
import cv2
import numpy as np
import onnxruntime
from utils import draw_detections
class YOLOv10:
def __init__(self, path):
# Initialize model
self.initialize_model(path)
def __call__(self, image):
return self.detect_objects(image)
def initialize_model(self, path):
self.session = onnxruntime.InferenceSession(
path, providers=onnxruntime.get_available_providers()
)
# Get model info
self.get_input_details()
self.get_output_details()
def detect_objects(self, image, conf_threshold=0.3):
input_tensor = self.prepare_input(image)
# Perform inference on the image
new_image = self.inference(image, input_tensor, conf_threshold)
return new_image
def prepare_input(self, image):
self.img_height, self.img_width = image.shape[:2]
input_img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# Resize input image
input_img = cv2.resize(input_img, (self.input_width, self.input_height))
# Scale input pixel values to 0 to 1
input_img = input_img / 255.0
input_img = input_img.transpose(2, 0, 1)
input_tensor = input_img[np.newaxis, :, :, :].astype(np.float32)
return input_tensor
def inference(self, image, input_tensor, conf_threshold=0.3):
start = time.perf_counter()
outputs = self.session.run(
self.output_names, {self.input_names[0]: input_tensor}
)
print(f"Inference time: {(time.perf_counter() - start)*1000:.2f} ms")
(
boxes,
scores,
class_ids,
) = self.process_output(outputs, conf_threshold)
return self.draw_detections(image, boxes, scores, class_ids)
def process_output(self, output, conf_threshold=0.3):
predictions = np.squeeze(output[0])
# Filter out object confidence scores below threshold
scores = predictions[:, 4]
predictions = predictions[scores > conf_threshold, :]
scores = scores[scores > conf_threshold]
if len(scores) == 0:
return [], [], []
# Get the class with the highest confidence
class_ids = np.argmax(predictions[:, 4:], axis=1)
# Get bounding boxes for each object
boxes = self.extract_boxes(predictions)
return boxes, scores, class_ids
def extract_boxes(self, predictions):
# Extract boxes from predictions
boxes = predictions[:, :4]
# Scale boxes to original image dimensions
boxes = self.rescale_boxes(boxes)
# Convert boxes to xyxy format
# boxes = xywh2xyxy(boxes)
return boxes
def rescale_boxes(self, boxes):
# Rescale boxes to original image dimensions
input_shape = np.array(
[self.input_width, self.input_height, self.input_width, self.input_height]
)
boxes = np.divide(boxes, input_shape, dtype=np.float32)
boxes *= np.array(
[self.img_width, self.img_height, self.img_width, self.img_height]
)
return boxes
def draw_detections(
self, image, boxes, scores, class_ids, draw_scores=True, mask_alpha=0.4
):
return draw_detections(image, boxes, scores, class_ids, mask_alpha)
def get_input_details(self):
model_inputs = self.session.get_inputs()
self.input_names = [model_inputs[i].name for i in range(len(model_inputs))]
self.input_shape = model_inputs[0].shape
self.input_height = self.input_shape[2]
self.input_width = self.input_shape[3]
def get_output_details(self):
model_outputs = self.session.get_outputs()
self.output_names = [model_outputs[i].name for i in range(len(model_outputs))]
if __name__ == "__main__":
import tempfile
import requests
from huggingface_hub import hf_hub_download
model_file = hf_hub_download(
repo_id="onnx-community/yolov10s", filename="onnx/model.onnx"
)
yolov8_detector = YOLOv10(model_file)
with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as f:
f.write(
requests.get(
"https://live.staticflickr.com/13/19041780_d6fd803de0_3k.jpg"
).content
)
f.seek(0)
img = cv2.imread(f.name)
# # Detect Objects
combined_image = yolov8_detector.detect_objects(img)
# Draw detections
cv2.namedWindow("Output", cv2.WINDOW_NORMAL)
cv2.imshow("Output", combined_image)
cv2.waitKey(0)

74
demo/old_app.py Normal file
View File

@@ -0,0 +1,74 @@
import os
import cv2
import gradio as gr
from gradio_webrtc import WebRTC
from huggingface_hub import hf_hub_download
from inference import YOLOv10
from twilio.rest import Client
model_file = hf_hub_download(
repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)
model = YOLOv10(model_file)
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def detection(frame, conf_threshold=0.3):
frame = cv2.flip(frame, 0)
return cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
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 (Powered by WebRTC ⚡️)
</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="Stream", rtc_configuration=rtc_configuration)
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
number = gr.Number()
image.stream(
fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
)
image.on_additional_outputs(lambda n: n, outputs=[number])
if __name__ == "__main__":
demo.launch()

6
demo/requirements.txt Normal file
View File

@@ -0,0 +1,6 @@
safetensors==0.4.3
opencv-python
twilio
https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/gradio-5.0.0b3-py3-none-any.whl
https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/gradio_webrtc-0.0.1-py3-none-any.whl
onnxruntime-gpu

321
demo/space.py Normal file
View File

@@ -0,0 +1,321 @@
import os
import gradio as gr
_docs = {
"WebRTC": {
"description": "Stream audio/video with WebRTC",
"members": {
"__init__": {
"rtc_configuration": {
"type": "dict[str, Any] | None",
"default": "None",
"description": "The configration dictionary to pass to the RTCPeerConnection constructor. If None, the default configuration is used.",
},
"height": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "str | None",
"default": "None",
"description": "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.",
},
"show_label": {
"type": "bool | None",
"default": "None",
"description": "if True, will display label.",
},
"container": {
"type": "bool",
"default": "True",
"description": "if True, will place the component in a container - providing some extra padding around the border.",
},
"scale": {
"type": "int | None",
"default": "None",
"description": "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": {
"type": "int",
"default": "160",
"description": "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": {
"type": "bool | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "if False, component will be hidden.",
},
"elem_id": {
"type": "str | None",
"default": "None",
"description": "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": {
"type": "list[str] | str | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "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": {
"type": "int | str | None",
"default": "None",
"description": "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": {
"type": "bool",
"default": "True",
"description": "if True webcam will be mirrored. Default is True.",
},
},
"events": {"tick": {"type": None, "default": None, "description": ""}},
},
"__meta__": {"additional_interfaces": {}, "user_fn_refs": {"WebRTC": []}},
}
}
abs_path = os.path.join(os.path.dirname(__file__), "css.css")
with gr.Blocks(
css_paths=abs_path,
theme=gr.themes.Default(
font_mono=[
gr.themes.GoogleFont("Inconsolata"),
"monospace",
],
),
) as demo:
gr.Markdown(
"""
<h1 style='text-align: center; margin-bottom: 1rem'> Gradio WebRTC ⚡️ </h1>
<div style="display: flex; flex-direction: row; justify-content: center">
<img style="display: block; padding-right: 5px; height: 20px;" alt="Static Badge" src="https://img.shields.io/badge/version%20-%200.0.5%20-%20orange">
<a href="https://github.com/freddyaboulton/gradio-webrtc" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/github-white?logo=github&logoColor=black"></a>
</div>
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
## Installation
```bash
pip install gradio_webrtc
```
## Examples:
1. [Object Detection from Webcam with YOLOv10](https://huggingface.co/spaces/freddyaboulton/webrtc-yolov10n) 📷
2. [Streaming Object Detection from Video with RT-DETR](https://huggingface.co/spaces/freddyaboulton/rt-detr-object-detection-webrtc) 🎥
3. [Text-to-Speech](https://huggingface.co/spaces/freddyaboulton/parler-tts-streaming-webrtc) 🗣️
## Usage
The WebRTC component supports the following three use cases:
1. Streaming video from the user webcam to the server and back
2. Streaming Video from the server to the client
3. Streaming Audio from the server to the client
Streaming Audio from client to the server and back (conversational AI) is not supported yet.
## Streaming Video from the User Webcam to the Server and Back
```python
import gradio as gr
from gradio_webrtc import WebRTC
def detection(image, conf_threshold=0.3):
... your detection code here ...
with gr.Blocks() as demo:
image = WebRTC(label="Stream", mode="send-receive", modality="video")
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
image.stream(
fn=detection,
inputs=[image, conf_threshold],
outputs=[image], time_limit=10
)
if __name__ == "__main__":
demo.launch()
```
* Set the `mode` parameter to `send-receive` and `modality` to "video".
* The `stream` event's `fn` parameter is a function that receives the next frame from the webcam
as a **numpy array** and returns the processed frame also as a **numpy array**.
* Numpy arrays are in (height, width, 3) format where the color channels are in RGB format.
* The `inputs` parameter should be a list where the first element is the WebRTC component. The only output allowed is the WebRTC component.
* The `time_limit` parameter is the maximum time in seconds the video stream will run. If the time limit is reached, the video stream will stop.
## Streaming Video from the User Webcam to the Server and Back
```python
import gradio as gr
from gradio_webrtc import WebRTC
import cv2
def generation():
url = "https://download.tsi.telecom-paristech.fr/gpac/dataset/dash/uhd/mux_sources/hevcds_720p30_2M.mp4"
cap = cv2.VideoCapture(url)
iterating = True
while iterating:
iterating, frame = cap.read()
yield frame
with gr.Blocks() as demo:
output_video = WebRTC(label="Video Stream", mode="receive", modality="video")
button = gr.Button("Start", variant="primary")
output_video.stream(
fn=generation, inputs=None, outputs=[output_video],
trigger=button.click
)
if __name__ == "__main__":
demo.launch()
```
* Set the "mode" parameter to "receive" and "modality" to "video".
* The `stream` event's `fn` parameter is a generator function that yields the next frame from the video as a **numpy array**.
* The only output allowed is the WebRTC component.
* The `trigger` parameter the gradio event that will trigger the webrtc connection. In this case, the button click event.
## Streaming Audio from the Server to the Client
```python
import gradio as gr
from pydub import AudioSegment
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file("/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav")
yield (segment.frame_rate, np.array(segment.get_array_of_samples()).reshape(1, -1))
with gr.Blocks() as demo:
audio = WebRTC(label="Stream", mode="receive", modality="audio")
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio],
trigger=button.click
)
```
* Set the "mode" parameter to "receive" and "modality" to "audio".
* The `stream` event's `fn` parameter is a generator function that yields the next audio segment as a tuple of (frame_rate, audio_samples).
* The numpy array should be of shape (1, num_samples).
* The `outputs` parameter should be a list with the WebRTC component as the only element.
## Deployment
When deploying in a cloud environment (like Hugging Face Spaces, EC2, etc), you need to set up a TURN server to relay the WebRTC traffic.
The easiest way to do this is to use a service like Twilio.
```python
from twilio.rest import Client
import os
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
with gr.Blocks() as demo:
...
rtc = WebRTC(rtc_configuration=rtc_configuration, ...)
...
```
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
##
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.ParamViewer(value=_docs["WebRTC"]["members"]["__init__"], linkify=[])
demo.load(
None,
js=r"""function() {
const refs = {};
const user_fn_refs = {
WebRTC: [], };
requestAnimationFrame(() => {
Object.entries(user_fn_refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}-user-fn`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
Object.entries(refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
})
}
""",
)
demo.launch()

53
demo/stream_whisper.py Normal file
View File

@@ -0,0 +1,53 @@
import tempfile
import gradio as gr
import numpy as np
from gradio_webrtc import AdditionalOutputs, ReplyOnPause, WebRTC
from openai import OpenAI
from pydub import AudioSegment
from dotenv import load_dotenv
load_dotenv()
client = OpenAI()
def transcribe(audio: tuple[int, np.ndarray], transcript: list[dict]):
print("audio", audio)
segment = AudioSegment(
audio[1].tobytes(),
frame_rate=audio[0],
sample_width=audio[1].dtype.itemsize,
channels=1,
)
transcript.append({"role": "user", "content": gr.Audio((audio[0], audio[1].squeeze()))})
with tempfile.NamedTemporaryFile(suffix=".mp3") as temp_audio:
segment.export(temp_audio.name, format="mp3")
next_chunk = client.audio.transcriptions.create(
model="whisper-1", file=open(temp_audio.name, "rb")
).text
transcript.append({"role": "assistant", "content": next_chunk})
yield AdditionalOutputs(transcript)
with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
audio = WebRTC(
label="Stream",
mode="send",
modality="audio",
)
with gr.Column():
transcript = gr.Chatbot(label="transcript", type="messages")
audio.stream(ReplyOnPause(transcribe), inputs=[audio, transcript], outputs=[audio],
time_limit=30)
audio.on_additional_outputs(lambda s: s, outputs=transcript)
if __name__ == "__main__":
demo.launch()

237
demo/utils.py Normal file
View File

@@ -0,0 +1,237 @@
import cv2
import numpy as np
class_names = [
"person",
"bicycle",
"car",
"motorcycle",
"airplane",
"bus",
"train",
"truck",
"boat",
"traffic light",
"fire hydrant",
"stop sign",
"parking meter",
"bench",
"bird",
"cat",
"dog",
"horse",
"sheep",
"cow",
"elephant",
"bear",
"zebra",
"giraffe",
"backpack",
"umbrella",
"handbag",
"tie",
"suitcase",
"frisbee",
"skis",
"snowboard",
"sports ball",
"kite",
"baseball bat",
"baseball glove",
"skateboard",
"surfboard",
"tennis racket",
"bottle",
"wine glass",
"cup",
"fork",
"knife",
"spoon",
"bowl",
"banana",
"apple",
"sandwich",
"orange",
"broccoli",
"carrot",
"hot dog",
"pizza",
"donut",
"cake",
"chair",
"couch",
"potted plant",
"bed",
"dining table",
"toilet",
"tv",
"laptop",
"mouse",
"remote",
"keyboard",
"cell phone",
"microwave",
"oven",
"toaster",
"sink",
"refrigerator",
"book",
"clock",
"vase",
"scissors",
"teddy bear",
"hair drier",
"toothbrush",
]
# Create a list of colors for each class where each color is a tuple of 3 integer values
rng = np.random.default_rng(3)
colors = rng.uniform(0, 255, size=(len(class_names), 3))
def nms(boxes, scores, iou_threshold):
# Sort by score
sorted_indices = np.argsort(scores)[::-1]
keep_boxes = []
while sorted_indices.size > 0:
# Pick the last box
box_id = sorted_indices[0]
keep_boxes.append(box_id)
# Compute IoU of the picked box with the rest
ious = compute_iou(boxes[box_id, :], boxes[sorted_indices[1:], :])
# Remove boxes with IoU over the threshold
keep_indices = np.where(ious < iou_threshold)[0]
# print(keep_indices.shape, sorted_indices.shape)
sorted_indices = sorted_indices[keep_indices + 1]
return keep_boxes
def multiclass_nms(boxes, scores, class_ids, iou_threshold):
unique_class_ids = np.unique(class_ids)
keep_boxes = []
for class_id in unique_class_ids:
class_indices = np.where(class_ids == class_id)[0]
class_boxes = boxes[class_indices, :]
class_scores = scores[class_indices]
class_keep_boxes = nms(class_boxes, class_scores, iou_threshold)
keep_boxes.extend(class_indices[class_keep_boxes])
return keep_boxes
def compute_iou(box, boxes):
# Compute xmin, ymin, xmax, ymax for both boxes
xmin = np.maximum(box[0], boxes[:, 0])
ymin = np.maximum(box[1], boxes[:, 1])
xmax = np.minimum(box[2], boxes[:, 2])
ymax = np.minimum(box[3], boxes[:, 3])
# Compute intersection area
intersection_area = np.maximum(0, xmax - xmin) * np.maximum(0, ymax - ymin)
# Compute union area
box_area = (box[2] - box[0]) * (box[3] - box[1])
boxes_area = (boxes[:, 2] - boxes[:, 0]) * (boxes[:, 3] - boxes[:, 1])
union_area = box_area + boxes_area - intersection_area
# Compute IoU
iou = intersection_area / union_area
return iou
def xywh2xyxy(x):
# Convert bounding box (x, y, w, h) to bounding box (x1, y1, x2, y2)
y = np.copy(x)
y[..., 0] = x[..., 0] - x[..., 2] / 2
y[..., 1] = x[..., 1] - x[..., 3] / 2
y[..., 2] = x[..., 0] + x[..., 2] / 2
y[..., 3] = x[..., 1] + x[..., 3] / 2
return y
def draw_detections(image, boxes, scores, class_ids, mask_alpha=0.3):
det_img = image.copy()
img_height, img_width = image.shape[:2]
font_size = min([img_height, img_width]) * 0.0006
text_thickness = int(min([img_height, img_width]) * 0.001)
# det_img = draw_masks(det_img, boxes, class_ids, mask_alpha)
# Draw bounding boxes and labels of detections
for class_id, box, score in zip(class_ids, boxes, scores):
color = colors[class_id]
draw_box(det_img, box, color)
label = class_names[class_id]
caption = f"{label} {int(score * 100)}%"
draw_text(det_img, caption, box, color, font_size, text_thickness)
return det_img
def draw_box(
image: np.ndarray,
box: np.ndarray,
color: tuple[int, int, int] = (0, 0, 255),
thickness: int = 2,
) -> np.ndarray:
x1, y1, x2, y2 = box.astype(int)
return cv2.rectangle(image, (x1, y1), (x2, y2), color, thickness)
def draw_text(
image: np.ndarray,
text: str,
box: np.ndarray,
color: tuple[int, int, int] = (0, 0, 255),
font_size: float = 0.001,
text_thickness: int = 2,
) -> np.ndarray:
x1, y1, x2, y2 = box.astype(int)
(tw, th), _ = cv2.getTextSize(
text=text,
fontFace=cv2.FONT_HERSHEY_SIMPLEX,
fontScale=font_size,
thickness=text_thickness,
)
th = int(th * 1.2)
cv2.rectangle(image, (x1, y1), (x1 + tw, y1 - th), color, -1)
return cv2.putText(
image,
text,
(x1, y1),
cv2.FONT_HERSHEY_SIMPLEX,
font_size,
(255, 255, 255),
text_thickness,
cv2.LINE_AA,
)
def draw_masks(
image: np.ndarray, boxes: np.ndarray, classes: np.ndarray, mask_alpha: float = 0.3
) -> np.ndarray:
mask_img = image.copy()
# Draw bounding boxes and labels of detections
for box, class_id in zip(boxes, classes):
color = colors[class_id]
x1, y1, x2, y2 = box.astype(int)
# Draw fill rectangle in mask image
cv2.rectangle(mask_img, (x1, y1), (x2, y2), color, -1)
return cv2.addWeighted(mask_img, mask_alpha, image, 1 - mask_alpha, 0)

65
demo/video_out.py Normal file
View File

@@ -0,0 +1,65 @@
import os
import cv2
import gradio as gr
from gradio_webrtc import WebRTC
from twilio.rest import Client
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation(input_video):
cap = cv2.VideoCapture(input_video)
iterating = True
while iterating:
iterating, frame = cap.read()
# flip frame vertically
frame = cv2.flip(frame, 0)
display_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
yield display_frame
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Video Streaming (Powered by WebRTC ⚡️)
</h1>
"""
)
with gr.Row():
with gr.Column():
input_video = gr.Video(sources="upload")
with gr.Column():
output_video = WebRTC(
label="Video Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="video",
)
output_video.stream(
fn=generation,
inputs=[input_video],
outputs=[output_video],
trigger=input_video.upload,
)
if __name__ == "__main__":
demo.launch()

54
demo/video_out_stream.py Normal file
View File

@@ -0,0 +1,54 @@
import os
import cv2
import gradio as gr
from gradio_webrtc import WebRTC
from twilio.rest import Client
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation():
url = "https://download.tsi.telecom-paristech.fr/gpac/dataset/dash/uhd/mux_sources/hevcds_720p30_2M.mp4"
cap = cv2.VideoCapture(url)
iterating = True
while iterating:
iterating, frame = cap.read()
yield frame
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Video Streaming (Powered by WebRTC ⚡️)
</h1>
"""
)
output_video = WebRTC(
label="Video Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="video",
)
button = gr.Button("Start", variant="primary")
output_video.stream(
fn=generation, inputs=None, outputs=[output_video], trigger=button.click
)
if __name__ == "__main__":
demo.launch()

100
demo/video_send_output.py Normal file
View File

@@ -0,0 +1,100 @@
import logging
import os
import random
import cv2
import gradio as gr
from gradio_webrtc import AdditionalOutputs, WebRTC
from huggingface_hub import hf_hub_download
from inference import YOLOv10
from twilio.rest import Client
# Configure the root logger to WARNING to suppress debug messages from other libraries
logging.basicConfig(level=logging.WARNING)
# Create a console handler
console_handler = logging.FileHandler("gradio_webrtc.log")
console_handler.setLevel(logging.DEBUG)
# Create a formatter
formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
console_handler.setFormatter(formatter)
# Configure the logger for your specific library
logger = logging.getLogger("gradio_webrtc")
logger.setLevel(logging.DEBUG)
logger.addHandler(console_handler)
model_file = hf_hub_download(
repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)
model = YOLOv10(model_file)
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def detection(frame, conf_threshold=0.3):
print("frame.shape", frame.shape)
frame = cv2.flip(frame, 0)
return AdditionalOutputs(1)
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 (Powered by WebRTC ⚡️)
</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="Stream", rtc_configuration=rtc_configuration,
mode="send",
track_constraints={"width": {"exact": 800},
"height": {"exact": 600},
"aspectRatio": {"exact": 1.33333}
},
rtp_params={"degradationPreference": "maintain-resolution"}
)
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
number = gr.Number()
image.stream(
fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
)
image.on_additional_outputs(lambda n: n, outputs=number)
demo.launch()