diff --git a/README.md b/README.md index 5ddb403..bec0b37 100644 --- a/README.md +++ b/README.md @@ -7,25 +7,22 @@

-Stream video and audio in real time with Gradio using WebRTC. +Stream video and audio in real time with Gradio using WebRTC. + +![picture-in-picture](docs/image.png) +![side-by-side](docs/image2.png) +

## Installation ```bash -pip install gradio_webrtc +gradio cc install +gradio cc build --no-generate-docs ``` -to use built-in pause detection (see [ReplyOnPause](https://freddyaboulton.github.io/gradio-webrtc//user-guide/#reply-on-pause)), install the `vad` extra: - ```bash -pip install gradio_webrtc[vad] -``` - -For stop word detection (see [ReplyOnStopWords](https://freddyaboulton.github.io/gradio-webrtc//user-guide/#reply-on-stopwords)), install the `stopword` extra: - -```bash -pip install gradio_webrtc[stopword] +pip install dist/gradio_webrtc-0.0.30.dev0-py3-none-any.whl ``` ## Docs @@ -34,385 +31,113 @@ https://freddyaboulton.github.io/gradio-webrtc/ ## Examples - - - - - +```python +import asyncio +import base64 +from io import BytesIO - - - - - - - - - - - - - - - - - - - - - - - - -
-

🗣️ Audio Input/Output with mini-omni2

-

Build a GPT-4o like experience with mini-omni2, an audio-native LLM.

- -

-Demo | -Code -

-		 -

🗣️ Talk to Claude

-

Use the Anthropic and Play.Ht APIs to have an audio conversation with Claude.

- -

-Demo | -Code -

-
-

🗣️ Kyutai Moshi

-

Kyutai's moshi is a novel speech-to-speech model for modeling human conversations.

- -

-Demo | -Code -

-		 -

🗣️ Hello Llama: Stop Word Detection

-

A code editor built with Llama 3.3 70b that is triggered by the phrase "Hello Llama". Build a Siri-like coding assistant in 100 lines of code!

- -

-Demo | -Code -

-
-

🤖 Llama Code Editor

-

Create and edit HTML pages with just your voice! Powered by SambaNova systems.

- -

-Demo | -Code -

-		 -

🗣️ Talk to Ultravox

-

Talk to Fixie.AI's audio-native Ultravox LLM with the transformers library.

- -

-Demo | -Code -

-
-

🗣️ Talk to Llama 3.2 3b

-

Use the Lepton API to make Llama 3.2 talk back to you!

- -

-Demo | -Code -

-		 -

🤖 Talk to Qwen2-Audio

-

Qwen2-Audio is a SOTA audio-to-text LLM developed by Alibaba.

- -

-Demo | -Code -

-
-

📷 Yolov10 Object Detection

-

Run the Yolov10 model on a user webcam stream in real time!

- -

-Demo | -Code -

-		 -

📷 Video Object Detection with RT-DETR

-

Upload a video and stream out frames with detected objects (powered by RT-DETR) model.

-

-Demo | -Code -

-
-

🔊 Text-to-Speech with Parler

-

Stream out audio generated by Parler TTS!

-

-Demo | -Code -

-		 -
- -## Usage - -This is an shortened version of the official [usage guide](https://freddyaboulton.github.io/gradio-webrtc/user-guide/). - -To get started with WebRTC streams, all that's needed is to import the `WebRTC` component from this package and implement its `stream` event. - -### Reply on Pause - -Typically, you want to run an AI model that generates audio when the user has stopped speaking. This can be done by wrapping a python generator with the `ReplyOnPause` class -and passing it to the `stream` event of the `WebRTC` component. - -```py import gradio as gr -from gradio_webrtc import WebRTC, ReplyOnPause - -def response(audio: tuple[int, np.ndarray]): # (1) - """This function must yield audio frames""" - ... - for numpy_array in generated_audio: - yield (sampling_rate, numpy_array, "mono") # (2) +import numpy as np +from gradio_webrtc import ( + AsyncAudioVideoStreamHandler, + WebRTC, + VideoEmitType, + AudioEmitType, +) +from PIL import Image -with gr.Blocks() as demo: - gr.HTML( - """ -

- Chat (Powered by WebRTC ⚡️) -

- """ - ) - with gr.Column(): - with gr.Group(): - audio = WebRTC( - mode="send-receive", # (3) - modality="audio", - ) - audio.stream(fn=ReplyOnPause(response), - inputs=[audio], outputs=[audio], # (4) - time_limit=60) # (5) - -demo.launch() -``` - -1. The python generator will receive the **entire** audio up until the user stopped. It will be a tuple of the form (sampling_rate, numpy array of audio). The array will have a shape of (1, num_samples). You can also pass in additional input components. - -2. The generator must yield audio chunks as a tuple of (sampling_rate, numpy audio array). Each numpy audio array must have a shape of (1, num_samples). - -3. The `mode` and `modality` arguments must be set to `"send-receive"` and `"audio"`. - -4. The `WebRTC` component must be the first input and output component. - -5. Set a `time_limit` to control how long a conversation will last. If the `concurrency_count` is 1 (default), only one conversation will be handled at a time. +def encode_audio(data: np.ndarray) -> dict: + """Encode Audio data to send to the server""" + return {"mime_type": "audio/pcm", "data": base64.b64encode(data.tobytes()).decode("UTF-8")} -### Reply On Stopwords - -You can configure your AI model to run whenever a set of "stop words" are detected, like "Hey Siri" or "computer", with the `ReplyOnStopWords` class. - -The API is similar to `ReplyOnPause` with the addition of a `stop_words` parameter. +def encode_image(data: np.ndarray) -> dict: + with BytesIO() as output_bytes: + pil_image = Image.fromarray(data) + pil_image.save(output_bytes, "JPEG") + bytes_data = output_bytes.getvalue() + base64_str = str(base64.b64encode(bytes_data), "utf-8") + return {"mime_type": "image/jpeg", "data": base64_str} -```py -import gradio as gr -from gradio_webrtc import WebRTC, ReplyOnPause +class VideoChatHandler(AsyncAudioVideoStreamHandler): + def __init__( + self, expected_layout="mono", output_sample_rate=24000, output_frame_size=480 + ) -> None: + super().__init__( + expected_layout, + output_sample_rate, + output_frame_size, + input_sample_rate=24000, + ) + self.audio_queue = asyncio.Queue() + self.video_queue = asyncio.Queue() + self.quit = asyncio.Event() + self.session = None + self.last_frame_time = 0 -def response(audio: tuple[int, np.ndarray]): - """This function must yield audio frames""" - ... - for numpy_array in generated_audio: - yield (sampling_rate, numpy_array, "mono") + def copy(self) -> "VideoChatHandler": + return VideoChatHandler( + expected_layout=self.expected_layout, + output_sample_rate=self.output_sample_rate, + output_frame_size=self.output_frame_size, + ) + async def video_receive(self, frame: np.ndarray): + newFrame = np.array(frame) + newFrame[0:, :, 0] = 255 - newFrame[0:, :, 0] + self.video_queue.put_nowait(newFrame) -with gr.Blocks() as demo: - gr.HTML( - """ -

- Chat (Powered by WebRTC ⚡️) -

- """ - ) - with gr.Column(): - with gr.Group(): - audio = WebRTC( - mode="send", - modality="audio", - ) - webrtc.stream(ReplyOnStopWords(generate, - input_sample_rate=16000, - stop_words=["computer"]), # (1) - inputs=[webrtc, history, code], - outputs=[webrtc], time_limit=90, - concurrency_limit=10) + async def video_emit(self) -> VideoEmitType: + return await self.video_queue.get() -demo.launch() -``` + async def receive(self, frame: tuple[int, np.ndarray]) -> None: + frame_size, array = frame + self.audio_queue.put_nowait(array) -1. The `stop_words` can be single words or pairs of words. Be sure to include common misspellings of your word for more robust detection, e.g. "llama", "lamma". In my experience, it's best to use two very distinct words like "ok computer" or "hello iris". - + async def emit(self) -> AudioEmitType: + if not self.args_set.is_set(): + await self.wait_for_args() + array = await self.audio_queue.get() + return (self.output_sample_rate, array) -### Audio Server-To-Clien - -To stream only from the server to the client, implement a python generator and pass it to the component's `stream` event. The stream event must also specify a `trigger` corresponding to a UI interaction that starts the stream. In this case, it's a button click. + def shutdown(self) -> None: + self.quit.set() + self.connection = None + self.args_set.clear() + self.quit.clear() -```py -import gradio as gr -from gradio_webrtc import WebRTC -from pydub import AudioSegment +css = """ +footer { + display: none !important; +} +""" -def generation(num_steps): - for _ in range(num_steps): - segment = AudioSegment.from_file("audio_file.wav") - array = np.array(segment.get_array_of_samples()).reshape(1, -1) - yield (segment.frame_rate, array) +with gr.Blocks(css=css) as demo: + webrtc = WebRTC( + label="Video Chat", + modality="audio-video", + mode="send-receive", + video_chat=True, + elem_id="video-source", + ) + webrtc.stream( + VideoChatHandler(), + inputs=[webrtc], + outputs=[webrtc], + time_limit=150, + concurrency_limit=2, + ) -with gr.Blocks() as demo: - audio = WebRTC(label="Stream", mode="receive", # (1) - 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 # (2) - ) -``` - -1. Set `mode="receive"` to only receive audio from the server. -2. The `stream` event must take a `trigger` that corresponds to the gradio event that starts the stream. In this case, it's the button click. - - -### Video Input/Output Streaming -Set up a video Input/Output stream to continuosly receive webcam frames from the user and run an arbitrary python function to return a modified frame. - -```py -import gradio as gr -from gradio_webrtc import WebRTC - - -def detection(image, conf_threshold=0.3): # (1) - ... your detection code here ... - return modified_frame # (2) - - -with gr.Blocks() as demo: - image = WebRTC(label="Stream", mode="send-receive", modality="video") # (3) - 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], # (4) - outputs=[image], time_limit=10 - ) if __name__ == "__main__": demo.launch() + ``` -1. The webcam frame will be represented as a numpy array of shape (height, width, RGB). -2. The function must return a numpy array. It can take arbitrary values from other components. -3. Set the `modality="video"` and `mode="send-receive"` -4. The `inputs` parameter should be a list where the first element is the WebRTC component. The only output allowed is the WebRTC component. - -### Server-to-Client Only - -Set up a server-to-client stream to stream video from an arbitrary user interaction. - -```py -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 # (1) - -with gr.Blocks() as demo: - output_video = WebRTC(label="Video Stream", mode="receive", # (2) - modality="video") - button = gr.Button("Start", variant="primary") - output_video.stream( - fn=generation, inputs=None, outputs=[output_video], - trigger=button.click # (3) - ) - demo.launch() -``` - -1. The `stream` event's `fn` parameter is a generator function that yields the next frame from the video as a **numpy array**. -2. Set `mode="receive"` to only receive audio from the server. -3. The `trigger` parameter the gradio event that will trigger the stream. In this case, the button click event. - - -### Additional Outputs - -In order to modify other components from within the WebRTC stream, you must yield an instance of `AdditionalOutputs` and add an `on_additional_outputs` event to the `WebRTC` component. - -This is common for displaying a multimodal text/audio conversation in a Chatbot UI. - - - -``` py title="Additional Outputs" -from gradio_webrtc import AdditionalOutputs, WebRTC - -def transcribe(audio: tuple[int, np.ndarray], - transformers_convo: list[dict], - gradio_convo: list[dict]): - response = model.generate(**inputs, max_length=256) - transformers_convo.append({"role": "assistant", "content": response}) - gradio_convo.append({"role": "assistant", "content": response}) - yield AdditionalOutputs(transformers_convo, gradio_convo) # (1) - - -with gr.Blocks() as demo: - gr.HTML( - """ -

- Talk to Qwen2Audio (Powered by WebRTC ⚡️) -

- """ - ) - transformers_convo = gr.State(value=[]) - with gr.Row(): - with gr.Column(): - audio = WebRTC( - label="Stream", - mode="send", # (2) - modality="audio", - ) - with gr.Column(): - transcript = gr.Chatbot(label="transcript", type="messages") - - audio.stream(ReplyOnPause(transcribe), - inputs=[audio, transformers_convo, transcript], - outputs=[audio], time_limit=90) - audio.on_additional_outputs(lambda s,a: (s,a), # (3) - outputs=[transformers_convo, transcript], - queue=False, show_progress="hidden") - demo.launch() -``` - - 1. Pass your data to `AdditionalOutputs` and yield it. - 2. In this case, no audio is being returned, so we set `mode="send"`. However, if we set `mode="send-receive"`, we could also yield generated audio and `AdditionalOutputs`. - 3. The `on_additional_outputs` event does not take `inputs`. It's common practice to not run this event on the queue since it is just a quick UI update. -=== "Notes" - 1. Pass your data to `AdditionalOutputs` and yield it. - 2. In this case, no audio is being returned, so we set `mode="send"`. However, if we set `mode="send-receive"`, we could also yield generated audio and `AdditionalOutputs`. - 3. The `on_additional_outputs` event does not take `inputs`. It's common practice to not run this event on the queue since it is just a quick UI update. - - ## 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. @@ -438,4 +163,4 @@ with gr.Blocks() as demo: ... rtc = WebRTC(rtc_configuration=rtc_configuration, ...) ... -``` \ No newline at end of file +``` diff --git a/demo/app.py b/demo/app.py index ee987ea..7a5bd53 100644 --- a/demo/app.py +++ b/demo/app.py @@ -1,7 +1,5 @@ import asyncio import base64 -import os -import time from io import BytesIO import gradio as gr @@ -9,7 +7,6 @@ import numpy as np from gradio_webrtc import ( AsyncAudioVideoStreamHandler, WebRTC, - async_aggregate_bytes_to_16bit, VideoEmitType, AudioEmitType, ) @@ -30,7 +27,7 @@ def encode_image(data: np.ndarray) -> dict: return {"mime_type": "image/jpeg", "data": base64_str} -class GeminiHandler(AsyncAudioVideoStreamHandler): +class VideoChatHandler(AsyncAudioVideoStreamHandler): def __init__( self, expected_layout="mono", output_sample_rate=24000, output_frame_size=480 ) -> None: @@ -46,8 +43,8 @@ class GeminiHandler(AsyncAudioVideoStreamHandler): self.session = None self.last_frame_time = 0 - def copy(self) -> "GeminiHandler": - return GeminiHandler( + def copy(self) -> "VideoChatHandler": + return VideoChatHandler( expected_layout=self.expected_layout, output_sample_rate=self.output_sample_rate, output_frame_size=self.output_frame_size, @@ -102,7 +99,7 @@ with gr.Blocks(css=css) as demo: elem_id="video-source", ) webrtc.stream( - GeminiHandler(), + VideoChatHandler(), inputs=[webrtc], outputs=[webrtc], time_limit=150, diff --git a/docs/image.png b/docs/image.png new file mode 100644 index 0000000..643f800 Binary files /dev/null and b/docs/image.png differ diff --git a/docs/image2.png b/docs/image2.png new file mode 100644 index 0000000..166bebb Binary files /dev/null and b/docs/image2.png differ