Automatic Speech Recognition
MLX
German
whisper
Eval Results
cstr commited on
Commit
e4f9e82
1 Parent(s): 35ce3b0

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +19 -0
  2. config.json +17 -0
  3. weights.npz +3 -0
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: mlx
3
+ ---
4
+
5
+ # whisper-large-v3-turbo-german-f16-q4
6
+ This model was converted to MLX format.
7
+
8
+ ## Use with MLX
9
+
10
+ ```bash
11
+ git clone https://github.com/ml-explore/mlx-examples.git
12
+ cd mlx-examples/whisper/
13
+ pip install -r requirements.txt
14
+
15
+ # Example usage
16
+ import mlx_whisper
17
+ result = mlx_whisper.transcribe("test.mp3", path_or_hf_repo="whisper-large-v3-turbo-german-f16-q4")
18
+ print(result)
19
+ ```
config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4,
12
+ "quantization": {
13
+ "group_size": 64,
14
+ "bits": 4
15
+ },
16
+ "model_type": "whisper"
17
+ }
weights.npz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5648330946342b019dd6286a06cd212ec2ffde4130f83d3f19acb509fc814241
3
+ size 728628832