Whisper-can / app.py
henryu's picture
Update app.py
fbeca34
import torch
import gradio as gr
import pytube as pt
from transformers import pipeline
from huggingface_hub import model_info
import openai
def transcribe(microphone, file_upload):
warn_output = ""
if (microphone is not None) and (file_upload is not None):
warn_output = (
"WARNING: You've uploaded an audio file and used the microphone. "
"The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
)
elif (microphone is None) and (file_upload is None):
return "ERROR: You have to either use the microphone or upload an audio file"
file = microphone if microphone is not None else file_upload
openai.api_key = "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"
device = 0 if torch.cuda.is_available() else "cpu"
res_format = 'srt'
transcript = openai.Audio.transcribe(model="whisper-1", file=open(file, 'rb'), response_format=res_format, prompt='请使用书面语')
text = transcript
return warn_output + text
def _return_yt_html_embed(yt_url):
video_id = yt_url.split("?v=")[-1]
HTML_str = (
f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
" </center>"
)
return HTML_str
def yt_transcribe(yt_url):
yt = pt.YouTube(yt_url)
html_embed_str = _return_yt_html_embed(yt_url)
stream = yt.streams.filter(only_audio=True)[0]
stream.download(filename="audio.mp3")
openai.api_key = "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"
device = 0 if torch.cuda.is_available() else "cpu"
res_format = 'srt'
transcript = openai.Audio.transcribe(model="whisper-1", file=open('audio.mp3', 'rb'), response_format=res_format, prompt='请使用书面语')
text = transcript
return html_embed_str, text
demo = gr.Blocks()
mf_transcribe = gr.Interface(
fn=transcribe,
inputs=[
gr.inputs.Audio(source="microphone", type="filepath", optional=True),
gr.inputs.Audio(source="upload", type="filepath", optional=True),
],
outputs="text",
layout="horizontal",
theme="huggingface",
title="Whisper Demo: Transcribe Audio",
description=(
"Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the Whisper."
),
allow_flagging="never",
)
yt_transcribe = gr.Interface(
fn=yt_transcribe,
inputs=[gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL")],
outputs=["html", "text"],
layout="horizontal",
theme="huggingface",
title="Whisper Demo: Transcribe YouTube",
description=(
"Transcribe long-form YouTube videos with the click of a button! Demo uses the Whisper."
),
allow_flagging="never",
)
with demo:
gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
demo.launch(enable_queue=True)