Views
No views yet
pip install -U mlx-whispermlx_whisper audio.wav --model doggy8088/whisper-large-v2-cantonese-mlx-4bit --language zh1import mlx_whisper
2
3result = mlx_whisper.transcribe(
4 "audio.wav",
5 path_or_hf_repo="doggy8088/whisper-large-v2-cantonese-mlx-4bit",
6 language="zh",
7)
8print(result["text"])language="zh"，或省略讓模型自動偵測；不要指定 yue。