Automatic Speech Recognition
MLX
Safetensors
moss_transcribe_diarize
speaker-diarization
ios
korean
custom_code
Instructions to use WJO/MOSS-Transcribe-Diarize-MLX-q8all-e8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use WJO/MOSS-Transcribe-Diarize-MLX-q8all-e8 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download WJO/MOSS-Transcribe-Diarize-MLX-q8all-e8 --local-dir MOSS-Transcribe-Diarize-MLX-q8all-e8
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
MOSS Transcribe Diarize ยท MLX q8all-e8
OpenMOSS-Team/MOSS-Transcribe-Diarize๋ฅผ Apple Silicon๊ณผ iPhone์ MLX Swift ๋ฐํ์์์ ์ฌ์ฉํ๊ธฐ ์ํด ๋ณํํ 8-bit ๋ฐฐํฌ๋ณธ์
๋๋ค.
- ์ ํ ๊ณ์ธต: affine 8-bit, group size 64
- ํ ํฐ ์๋ฒ ๋ฉ: affine 8-bit, group size 64
- ๋์ ๋ฐํ์: Substream
MossTranscriptionKit - ๊ธฐ๋ณธ ๋ชจ๋ธ ๋ผ์ด์ ์ค: Apache-2.0
์๋ณธ BF16 ์ฒดํฌํฌ์ธํธ์ ์คํ ํ์์ด ๋ค๋ฆ ๋๋ค. Substream iOS ์ฑ์์๋ ์ค์ โ ๊ธฐ๊ธฐ ๋ด ๋ชจ๋ธ โ MOSS ์จ๋๋ฐ์ด์ค์์ ์ด ์ ์ฅ์๋ฅผ ์ง์ ๋ค์ด๋ก๋ํ๊ณ , ๊ตฌ์ฑยทํฌ๊ธฐยท์์ํ ๋ชจ๋ยทSHA-256 manifest๋ฅผ ๊ฒ์ฆํ ๋ค ์ค์นํฉ๋๋ค.
- Downloads last month
- 14
Model size
0.5B params
Tensor type
F16
ยท
U32 ยท
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for WJO/MOSS-Transcribe-Diarize-MLX-q8all-e8
Base model
OpenMOSS-Team/MOSS-Transcribe-Diarize