Instructions to use FredrikKarlssonSpeech/whisper-large-finnish-v3-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FredrikKarlssonSpeech/whisper-large-finnish-v3-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir whisper-large-finnish-v3-mlx FredrikKarlssonSpeech/whisper-large-finnish-v3-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Add MLX-converted Whisper weights
Browse files- README.md +32 -0
- config.json +13 -0
- weights.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- fi
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: mlx
|
| 6 |
+
tags:
|
| 7 |
+
- automatic-speech-recognition
|
| 8 |
+
- whisper
|
| 9 |
+
- mlx
|
| 10 |
+
- fi
|
| 11 |
+
base_model: Finnish-NLP/whisper-large-finnish-v3
|
| 12 |
+
pipeline_tag: automatic-speech-recognition
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# whisper-large-finnish-v3 (MLX, float16)
|
| 16 |
+
|
| 17 |
+
MLX conversion of [Finnish-NLP/whisper-large-finnish-v3](https://huggingface.co/Finnish-NLP/whisper-large-finnish-v3) for fast inference on Apple Silicon via [mlx-whisper](https://github.com/ml-explore/mlx-examples/tree/main/whisper).
|
| 18 |
+
|
| 19 |
+
Converted with `mlx-examples/whisper/convert.py` at `float16` precision.
|
| 20 |
+
|
| 21 |
+
## Usage
|
| 22 |
+
|
| 23 |
+
```bash
|
| 24 |
+
pip install mlx-whisper
|
| 25 |
+
mlx_whisper audio_file.mp3 --model FredrikKarlssonSpeech/whisper-large-finnish-v3-mlx
|
| 26 |
+
```
|
| 27 |
+
|
| 28 |
+
```python
|
| 29 |
+
import mlx_whisper
|
| 30 |
+
result = mlx_whisper.transcribe("audio_file.mp3", path_or_hf_repo="FredrikKarlssonSpeech/whisper-large-finnish-v3-mlx")
|
| 31 |
+
print(result["text"])
|
| 32 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"n_mels": 128,
|
| 3 |
+
"n_audio_ctx": 1500,
|
| 4 |
+
"n_audio_state": 1280,
|
| 5 |
+
"n_audio_head": 20,
|
| 6 |
+
"n_audio_layer": 32,
|
| 7 |
+
"n_vocab": 51866,
|
| 8 |
+
"n_text_ctx": 448,
|
| 9 |
+
"n_text_state": 1280,
|
| 10 |
+
"n_text_head": 20,
|
| 11 |
+
"n_text_layer": 32,
|
| 12 |
+
"model_type": "whisper"
|
| 13 |
+
}
|
weights.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fc1fa865b266c95ffdc3da3d9e488829d0e4e107c2e93fc9eb799c2527c7067
|
| 3 |
+
size 3083280590
|