c

app.py

@@ -1,32 +0,0 @@
-import gradio as gr
-from pytube import YouTube
-import subprocess
-from huggingsound import SpeechRecognitionModel
-import torch
-import librosa
-import soundfile as sf
-from transformers import pipeline
-
-def process_video(video_url):
-    yt = YouTube(video_url)
-    audio_file = yt.streams.filter(only_audio=True, file_extension='mp4').first().download(filename='ytaudio.mp4')
-    subprocess.run(['ffmpeg', '-i', 'ytaudio.mp4', '-acodec', 'pcm_s16le', '-ar', '16000', 'ytaudio.wav'])
-    
-    device = "cuda" if torch.cuda.is_available() else "cpu"
-    model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-english", device=device)
-    
-    input_file = 'ytaudio.wav'
-    stream = librosa.stream(input_file, block_length=30, frame_length=16000, hop_length=16000)
-    
-    full_transcript = ''
-    for i, speech in enumerate(stream):
-        sf.write(f'{i}.wav', speech, 16000)
-        transcription = model.transcribe([f'{i}.wav'])[0]['transcription']
-        full_transcript += transcription + ' '
-
-    summarization = pipeline('summarization')
-    summarized_text = summarization(full_transcript, max_length=130, min_length=30, do_sample=False)
-    return summarized_text[0]['summary_text']
-
-iface = gr.Interface(fn=process_video, inputs="text", outputs="text", title="YouTube Video Summarizer")
-iface.launch()