whisperX 安装及测试

仓库地址：https://github.com/m-bain/whisperX

安装步骤

pip install whisperx
pip install ctranslate2==4.5.0

容易遇到报错：
Unable to load any of {libcudnn_cnn.so.9.1.0, libcudnn_cnn.so.9.1, libcudnn_cnn.so.9, libcudnn_cnn.so}

conda install -c conda-forge cudnn

import whisperx
import gc
from whisperx.diarize import DiarizationPipelinedevice = "cuda"
audio_file = "audio.mp3"
batch_size = 16 # reduce if low on GPU mem
compute_type = "float16" # change to "int8" if low on GPU mem (may reduce accuracy)# 1. Transcribe with original whisper (batched)
model = whisperx.load_model("large-v2", device, compute_type=compute_type)# save model to local path (optional)
# model_dir = "/path/"
# model = whisperx.load_model("large-v2", device, compute_type=compute_type, download_root=model_dir)audio = whisperx.load_audio(audio_file)
result = model.transcribe(audio, batch_size=batch_size)
print(result["segments"]) # before alignment# delete model if low on GPU resources
# import gc; import torch; gc.collect(); torch.cuda.empty_cache(); del model# 2. Align whisper output
model_a, metadata = whisperx.load_align_model(language_code=result["language"], device=device)
result = whisperx.align(result["segments"], model_a, metadata, audio, device, return_char_alignments=False)print(result["segments"]) # after alignment# delete model if low on GPU resources
# import gc; import torch; gc.collect(); torch.cuda.empty_cache(); del model_a# 3. Assign speaker labels
diarize_model = DiarizationPipeline(use_auth_token=YOUR_HF_TOKEN, device=device)# add min/max number of speakers if known
diarize_segments = diarize_model(audio)
# diarize_model(audio, min_speakers=min_speakers, max_speakers=max_speakers)result = whisperx.assign_word_speakers(diarize_segments, result)
print(diarize_segments)
print(result["segments"]) # segments are now assigned speaker IDs