mirror of
https://github.com/HumanAIGC-Engineering/gradio-webrtc.git
synced 2026-02-05 18:09:23 +08:00
853d6a06b5
* Add code * add code * add code * Rename messages * rename * add code * Add demo * docs + demos + bug fixes * add code * styles * user guide * Styles * Add code * misc docs updates * print nit * whisper + pr * url for images * whsiper update * Fix bugs * remove demo files * version number * Fix pypi readme * Fix * demos * Add llama code editor * Update llama code editor and object detection cookbook * Add more cookbook demos * add code * Fix links for PR deploys * add code * Fix the install * add tts * TTS docs * Typo * Pending bubbles for reply on pause * Stream redesign (#63) * better error handling * Websocket error handling * add code --------- Co-authored-by: Freddy Boulton <freddyboulton@hf-freddy.local> * remove docs from dist * Some docs typos * more typos * upload changes + docs * docs * better phone * update docs * add code * Make demos better * fix docs + websocket start_up * remove mention of FastAPI app * fastphone tweaks * add code * ReplyOnStopWord fixes * Fix cookbook * Fix pypi readme * add code * bump versions * sambanova cookbook * Fix tags * Llm voice chat * kyutai tag * Add error message to all index.html * STT module uses Moonshine * Not required from typing extensions * fix llm voice chat * Add vpn warning * demo fixes * demos * Add more ui args and gemini audio-video * update cookbook * version 9 --------- Co-authored-by: Freddy Boulton <freddyboulton@hf-freddy.local>
87 lines
2.2 KiB
Python
87 lines
2.2 KiB
Python
import json
|
|
from pathlib import Path
|
|
|
|
import gradio as gr
|
|
import numpy as np
|
|
from dotenv import load_dotenv
|
|
from fastapi import FastAPI
|
|
from fastapi.responses import HTMLResponse, StreamingResponse
|
|
from fastrtc import (
|
|
AdditionalOutputs,
|
|
ReplyOnPause,
|
|
Stream,
|
|
WebRTCError,
|
|
audio_to_bytes,
|
|
get_twilio_turn_credentials,
|
|
)
|
|
from gradio.utils import get_space
|
|
from groq import AsyncClient
|
|
|
|
cur_dir = Path(__file__).parent
|
|
|
|
load_dotenv()
|
|
|
|
|
|
groq_client = AsyncClient()
|
|
|
|
|
|
async def transcribe(audio: tuple[int, np.ndarray]):
|
|
try:
|
|
transcript = await groq_client.audio.transcriptions.create(
|
|
file=("audio-file.mp3", audio_to_bytes(audio)),
|
|
model="whisper-large-v3-turbo",
|
|
response_format="verbose_json",
|
|
)
|
|
yield AdditionalOutputs(transcript.text)
|
|
except Exception as e:
|
|
raise WebRTCError(str(e))
|
|
|
|
|
|
stream = Stream(
|
|
ReplyOnPause(transcribe),
|
|
modality="audio",
|
|
mode="send",
|
|
additional_outputs=[
|
|
gr.Textbox(label="Transcript"),
|
|
],
|
|
additional_outputs_handler=lambda a, b: a + " " + b,
|
|
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
|
|
concurrency_limit=5 if get_space() else None,
|
|
time_limit=90 if get_space() else None,
|
|
)
|
|
|
|
app = FastAPI()
|
|
|
|
stream.mount(app)
|
|
|
|
|
|
@app.get("/transcript")
|
|
def _(webrtc_id: str):
|
|
async def output_stream():
|
|
async for output in stream.output_stream(webrtc_id):
|
|
transcript = output.args[0]
|
|
yield f"event: output\ndata: {transcript}\n\n"
|
|
|
|
return StreamingResponse(output_stream(), media_type="text/event-stream")
|
|
|
|
|
|
@app.get("/")
|
|
def index():
|
|
rtc_config = get_twilio_turn_credentials() if get_space() else None
|
|
html_content = (cur_dir / "index.html").read_text()
|
|
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
|
|
return HTMLResponse(content=html_content)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import os
|
|
|
|
if (mode := os.getenv("MODE")) == "UI":
|
|
stream.ui.launch(server_port=7860, server_name="0.0.0.0")
|
|
elif mode == "PHONE":
|
|
stream.fastphone(host="0.0.0.0", port=7860)
|
|
else:
|
|
import uvicorn
|
|
|
|
uvicorn.run(app, host="0.0.0.0", port=7860)
|