fp16 Open on Hugging Face
Parameters
72M
Weights (est.)
≈ 144 MB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- openai-whisper-base
- Vendor
- —
- Task
- Speech recognition
- Quantisation
- fp16
- Licence
- apache-2.0
- Downloads
- 53 in the last 30 days · 369 all time · 0 likes
- Published
- 2025-03-15 · updated 2025-10-25 (1y ago)
- Languages
- km
- Tags
- whisper, Khmer, model-index
Other MLX builds of openai-whisper-base
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| whisper-base-khmer-mlx-fp16 (this one) | fp16 | ≈ 144 MB | 8 GB+ | 53 |
| whisper-base-khmer-mlx-fp32 | fp32 | ≈ 287 MB | 8 GB+ | 56 |