Instructions to use argmaxinc/whisperkit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use argmaxinc/whisperkit-mlx with WhisperKit:
# Install CLI with Homebrew on macOS device brew install whisperkit-cli # View all available inference options whisperkit-cli transcribe --help # Download and run inference using whisper base model whisperkit-cli transcribe --audio-path /path/to/audio.mp3 # Or use your preferred model variant whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path /path/to/audio.mp3 --verbose
- MLX
How to use argmaxinc/whisperkit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir whisperkit-mlx argmaxinc/whisperkit-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Added whisper-base
#1
by jkrukowski - opened
openai_whisper-base/config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"n_mels": 80,
|
| 3 |
+
"n_audio_ctx": 1500,
|
| 4 |
+
"n_audio_state": 512,
|
| 5 |
+
"n_audio_head": 8,
|
| 6 |
+
"n_audio_layer": 6,
|
| 7 |
+
"n_vocab": 51865,
|
| 8 |
+
"n_text_ctx": 448,
|
| 9 |
+
"n_text_state": 512,
|
| 10 |
+
"n_text_head": 8,
|
| 11 |
+
"n_text_layer": 6,
|
| 12 |
+
"model_type": "whisper"
|
| 13 |
+
}
|
openai_whisper-base/decoder.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:066dbf1a13b184d24ec529c80fdce71f14782b5a6be855751f78f68dbb211042
|
| 3 |
+
size 104020592
|
openai_whisper-base/encoder.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ae920f676f84979658343f6c9812671a5a43a725c4a7af147e434ada95eafd6
|
| 3 |
+
size 39653896
|