File size: 2,484 Bytes
b789fdf 6c74174 c3c6112 b789fdf cf75eeb 6c74174 8663026 6c74174 ff9c2e5 b789fdf c3c6112 6c74174 c3c6112 6c74174 ff9c2e5 6c74174 c3c6112 ff9c2e5 cf75eeb ff9c2e5 cf75eeb ff9c2e5 6c74174 cf75eeb ff9c2e5 6c74174 |
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 61 62 63 64 65 66 67 68 69 |
import gradio as gr
import torch
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC, pipeline
import soundfile as sf
import librosa
# Load models
# Transcription model for Moroccan Darija
processor = Wav2Vec2Processor.from_pretrained("boumehdi/wav2vec2-large-xlsr-moroccan-darija")
transcription_model = Wav2Vec2ForCTC.from_pretrained("boumehdi/wav2vec2-large-xlsr-moroccan-darija")
# Summarization model
summarizer = pipeline("summarization", model="t5-small")
# Function to resample audio to 16kHz if necessary
def resample_audio(audio_path, target_sr=16000):
audio_input, original_sr = librosa.load(audio_path, sr=None) # Load audio with original sampling rate
if original_sr != target_sr:
audio_input = librosa.resample(audio_input, orig_sr=original_sr, target_sr=target_sr) # Resample to 16kHz
return audio_input, target_sr
# Function to transcribe audio using Wav2Vec2
def transcribe_audio(audio_path):
# Load and preprocess audio
audio_input, sample_rate = resample_audio(audio_path)
inputs = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt", padding=True)
# Get predictions
with torch.no_grad():
logits = transcription_model(**inputs).logits
# Decode predictions
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.batch_decode(predicted_ids)[0]
return transcription
# Function to transcribe and summarize
def transcribe_and_summarize(audio_file):
# Transcription
transcription = transcribe_audio(audio_file)
# Check if transcription is long enough for summarization
if len(transcription.split()) < 10: # Check if the transcription is too short for summarization
summary = "Transcription is too short for summarization."
else:
# Summarization
summary = summarizer(transcription, max_length=50, min_length=10, do_sample=False)[0]["summary_text"]
return transcription, summary
# Gradio Interface
inputs = gr.Audio(type="filepath", label="Upload your audio file")
outputs = [
gr.Textbox(label="Transcription"),
gr.Textbox(label="Summary")
]
app = gr.Interface(
fn=transcribe_and_summarize,
inputs=inputs,
outputs=outputs,
title="Moroccan Darija Audio Transcription and Summarization",
description="Upload an audio file in Moroccan Darija to get its transcription and a summarized version of the content."
)
# Launch the app
if __name__ == "__main__":
app.launch()
|