whisper-large-v3-turbo-german-f16-q4
mlx-community/whisper-large-v3-turbo-german-f16-q4
Speech recognition · mlx
4-bit Open on Hugging Face
Parameters
—
Weights (est.)
—
Mac memory (est.)
—
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
- primeline/whisper-large-v3-german (finetune)
- Vendor
- primeline
- Task
- Speech recognition
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 175 in the last 30 days · 1.2K all time · 2 likes
- Published
- 2024-10-12 · updated 2024-10-12 (2y ago)
- Languages
- de
- Tags
- whisper, model-index
Other MLX builds of primeline/whisper-large-v3-german
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| whisper-large-v3-turbo-german-f16 | — | — | — | 378 |
| whisper-large-v3-turbo-german-f16-q4 (this one) | 4-bit | — | — | 175 |