gianTheo's picture
Create app.py
1858e5f
import os
from transformers import pipeline
import gradio as gr
import torch
import pytube as pt
checkpoint = "GGmorello/whisper-small-it"
device = 0 if torch.cuda.is_available() else "cpu"
print(device)
pipe = pipeline(task = "automatic-speech-recognition", model = checkpoint,chunk_length_s=30,device = device)
def transcribe(audio):
text = pipe(audio)["text"]
return text
def transcribe_url(yt_url):
yt = pt.YouTube(yt_url)
stream = yt.streams.filter(only_audio=True)[0]
stream.download(filename = "audio.mp3")
text = pipe("audio.mp3")["text"]
return text
demo = gr.Blocks()
microphone_interface = gr.Interface(
fn=transcribe,
inputs = gr.Audio(sources="microphone", type="filepath"),
outputs="text",
title="Whisper Small Italian Finetuned raw microphone audio",
description="Realtime demo for Italian speech recognition using a fine-tuned Whisper small model."
)
file_interface = gr.Interface(
fn=transcribe,
inputs = gr.Audio(sources="upload", type="filepath"),
outputs="text",
title="Whisper Small Italian Finetuned for audio file.",
description="Realtime demo for Italian speech recognition using a fine-tuned Whisper small model."
)
url_interface = gr.Interface(
fn = transcribe_url,
inputs = gr.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
outputs = "text",
title = "Whisper Small Italian Finetuned for URL transcription",
description = "Realtime demo for Italian speech recognition using a fine-tuned Whisper small model."
)
with demo:
gr.TabbedInterface([microphone_interface,file_interface, url_interface], ["Transcribe Audio", "Transcribe File" , "Transcribe YouTube"])
demo.launch(share=True)