whisperx

import whisperx import torch import os from pathlib import Path import requests # --- Setup for a runnable example --- # Path for the temporary audio file temp_audio_path = Path("temp_whisperx_example.wav") # A small WAV file from Mozilla DeepSpeech samples wav_url = "https://github.com/mozilla/DeepSpeech/raw/master/samples/audio/8455-210777-0068.wav" # Download a small audio file if it doesn't exist if not temp_audio_path.exists(): print(f"Downloading sample audio from {wav_url}...") try: response = requests.get(wav_url, stream=True) response.raise_for_status() with open(temp_audio_path, 'wb') as f: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) print("Sample audio downloaded.") except requests.exceptions.RequestException as e: print(f"Failed to download sample audio: {e}") print("Please ensure you have an internet connection or manually place a WAV file at temp_whisperx_example.wav") exit(1) # --- WhisperX Core Logic --- device = "cuda" if torch.cuda.is_available() else "cpu" # float16 for GPU, int8 for CPU or low VRAM GPU compute_type = "float16" if device == "cuda" else "int8" batch_size = 16 # Reduce if low on GPU VRAM print(f"\nLoading WhisperX model ('base') on {device} with {compute_type} precision...") # Using 'base' for faster download and less VRAM for quickstart model = whisperx.load_model("base", device, compute_type=compute_type, language="en") print(f"Loading audio from {temp_audio_path}...") audio = whisperx.load_audio(str(temp_audio_path)) print("Transcribing audio...") result = model.transcribe(audio, batch_size=batch_size) print("Loading alignment model and aligning segments...") model_a, metadata = whisperx.load_align_model(language_code=result["language"], device=device) aligned_result = whisperx.align(result["segments"], model_a, metadata, audio, device) print("\nTranscription Result (Aligned):") for segment in aligned_result["segments"]: print(f"[{segment['start']:.2f}s - {segment['end']:.2f}s]: {segment['text']}") # Optional: Add diarization for speaker assignment # Diarization models from Hugging Face may require an auth token. # Set your Hugging Face token as an environment variable (e.g., HF_TOKEN="hf_xxxx") hf_token = os.environ.get("HF_TOKEN", "") if hf_token: print("\nPerforming diarization (speaker assignment)...") # Diarization requires an internet connection to download models diarize_model = whisperx.DiarizationPipeline(use_auth_token=hf_token, device=device) diarize_segments = diarize_model(str(temp_audio_path), min_speakers=1, max_speakers=2) result_with_speakers = whisperx.assign_speakers(diarize_segments, aligned_result) print("\nTranscription with Speakers:") for segment in result_with_speakers["segments"]: print(f"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment.get('speaker', 'UNKNOWN')}: {segment['text']}") else: print("\nSkipping diarization: HF_TOKEN environment variable not found. Diarization models may require it.") # --- Cleanup --- temp_audio_path.unlink() print("\nWhisperX quickstart completed.")