Hugging Face's logo

dmatekenya
/
whisper-large-v3-chichewa

Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
dmatekenya commited on
Commit
6b31f2e
•
1 Parent(s): 888f08e

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -24
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
README.md CHANGED
@@ -4,26 +4,11 @@ license: apache-2.0
4
  base_model: openai/whisper-large-v3
5
  tags:
6
  - generated_from_trainer
7
- datasets:
8
- - audiofolder
9
  metrics:
10
  - wer
11
  model-index:
12
  - name: whisper-large-v3-chichewa
13
- results:
14
- - task:
15
- name: Automatic Speech Recognition
16
- type: automatic-speech-recognition
17
- dataset:
18
- name: audiofolder
19
- type: audiofolder
20
- config: default
21
- split: None
22
- args: default
23
- metrics:
24
- - name: Wer
25
- type: wer
26
- value: 65.67692307692307
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  # whisper-large-v3-chichewa
33
 
34
- This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the audiofolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 1.8894
37
- - Wer: 65.6769
38
 
39
  ## Model description
40
 
@@ -67,11 +52,11 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-------:|:----:|:---------------:|:-------:|
70
- | 0.0214 | 16.3934 | 1000 | 1.4932 | 69.6154 |
71
- | 0.0033 | 32.7869 | 2000 | 1.6484 | 66.0462 |
72
- | 0.0005 | 49.1803 | 3000 | 1.8019 | 65.6769 |
73
- | 0.0002 | 65.5738 | 4000 | 1.8711 | 65.1231 |
74
- | 0.0002 | 81.9672 | 5000 | 1.8894 | 65.6769 |
75
 
76
 
77
  ### Framework versions
 
4
  base_model: openai/whisper-large-v3
5
  tags:
6
  - generated_from_trainer
 
 
7
  metrics:
8
  - wer
9
  model-index:
10
  - name: whisper-large-v3-chichewa
11
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
16
 
17
  # whisper-large-v3-chichewa
18
 
19
+ This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.7213
22
+ - Wer: 77.8505
23
 
24
  ## Model description
25
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-------:|:----:|:---------------:|:-------:|
55
+ | 0.6163 | 7.4627 | 1000 | 1.8803 | 79.6019 |
56
+ | 0.1102 | 14.9254 | 2000 | 2.2954 | 81.6099 |
57
+ | 0.0654 | 22.3881 | 3000 | 2.5129 | 87.0942 |
58
+ | 0.0502 | 29.8507 | 4000 | 2.6569 | 77.7621 |
59
+ | 0.0482 | 37.3134 | 5000 | 2.7213 | 77.8505 |
60
 
61
 
62
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:747bace74483b8f21b7ca500c87471d920866bf1e312e429d304b9c8e0165896
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c276f2104b52610798cb90422db8466eb8e725fc3fe14e18129fbd0b8947ab6
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2c12bb4fa15223dcdf6fae99032471a1ff6609938cf35b8c140d93d5ec9b950
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55204c30bc4a33f75e874e04a72f373916319333866d58330a7ec843a890dc39
3
  size 1180663192