Downloads · 30 days
15
14% of all-time downloads
discus0434/kana-whisper-mlx-int8
kana-whisper-mlx-int8 is a automatic speech recognition model from discus0434. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as mit.
SB Intuitions の kana-whisper を Apple Silicon 向けの MLX 形式へ変換し、エンコーダーの Linear 層を INT8 へ量子化したモデル。
Downloads · 30 days
15
14% of all-time downloads
All-time downloads
106
Public
Repo size
1 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1 GB · 100%
From the Hugging Face model README
SB Intuitions の kana-whisper を Apple Silicon 向けの MLX 形式へ変換し、エンコーダーの Linear 層を INT8 へ量子化したモデル。
sbintuitions/kana-whisperpip install mlx-whisper==0.4.3
import mlx_whisper
result = mlx_whisper.transcribe(
"audio.wav",
path_or_hf_repo="discus0434/kana-whisper-mlx-int8",
language="ja",
task="transcribe",
temperature=0.0,
condition_on_previous_text=False,
)
print(result["text"])
MIT License。詳細は LICENSE を参照。