Automatic Speech Recognition
MLX
Yue Chinese
whisper
mlx-whisper
cantonese
4-bit precision
quantized
Instructions to use doggy8088/whisper-large-v2-cantonese-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use doggy8088/whisper-large-v2-cantonese-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir whisper-large-v2-cantonese-mlx-4bit doggy8088/whisper-large-v2-cantonese-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
whisper-large-v2-cantonese-mlx-4bit
這是 doggy8088/whisper-large-v2-cantonese-mlx 的 4-bit 量化版, 由原始的 MLX fp16 checkpoint 再量化而成,適合在 Apple Silicon 上進一步降低記憶體占用。
量化設定
- bits: 4
- group size: 64
- quantization mode: MLX affine weight-only quantization
使用方式
pip install -U mlx-whisper
CLI:
mlx_whisper audio.wav --model doggy8088/whisper-large-v2-cantonese-mlx-4bit --language zh
Python:
import mlx_whisper
result = mlx_whisper.transcribe(
"audio.wav",
path_or_hf_repo="doggy8088/whisper-large-v2-cantonese-mlx-4bit",
language="zh",
)
print(result["text"])
注意事項
- 這是量化模型,速度與精度可能和 fp16 版本略有差異。
- 建議使用
language="zh",或省略讓模型自動偵測;不要指定yue。 - 若你想要最高精度,請改用 fp16 原版:doggy8088/whisper-large-v2-cantonese-mlx
- Downloads last month
- 30
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for doggy8088/whisper-large-v2-cantonese-mlx-4bit
Base model
Scrya/whisper-large-v2-cantonese Finetuned
doggy8088/whisper-large-v2-cantonese-mlx