Spaces:
Sleeping
Sleeping
File size: 1,732 Bytes
1a4e81e 7e7af56 1a4e81e 7e7af56 1a4e81e 7e7af56 1a4e81e 7e7af56 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
from transformers import pipeline
import gradio as gr
import torch
import pytube as pt
checkpoint = "farsipal/whisper-small-el"
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 Greek Finetuned raw microphone audio",
description="Realtime demo for Greek 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 Greek Finetuned for audio file.",
description="Realtime demo for Greek 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 Greek Finetuned for URL transcription",
description = "Realtime demo for Greek 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) |