MathildeB3 commited on
Commit
92c28e7
·
verified ·
1 Parent(s): e4edb04

Model save

Browse files
README.md CHANGED
@@ -1,7 +1,5 @@
1
  ---
2
  library_name: transformers
3
- language:
4
- - fr
5
  license: apache-2.0
6
  base_model: openai/whisper-small
7
  tags:
@@ -9,19 +7,19 @@ tags:
9
  metrics:
10
  - wer
11
  model-index:
12
- - name: 52Hz Small Fr - IMT Atlantique X 52 Hertz
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # 52Hz Small Fr - IMT Atlantique X 52 Hertz
20
 
21
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Transcriptions IMTx52Hz v2 dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4085
24
- - Wer: 17.6471
25
 
26
  ## Model description
27
 
@@ -56,21 +54,21 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer |
58
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
59
- | 1.461 | 1.0 | 22 | 0.8945 | 41.0131 |
60
- | 0.6454 | 2.0 | 44 | 0.5209 | 25.4902 |
61
- | 0.3068 | 3.0 | 66 | 0.4752 | 21.0784 |
62
- | 0.2361 | 4.0 | 88 | 0.4253 | 19.9346 |
63
- | 0.1448 | 5.0 | 110 | 0.4112 | 19.7712 |
64
- | 0.1367 | 6.0 | 132 | 0.4118 | 17.9739 |
65
- | 0.0945 | 7.0 | 154 | 0.4220 | 19.6078 |
66
- | 0.0575 | 8.0 | 176 | 0.4065 | 16.9935 |
67
- | 0.0421 | 9.0 | 198 | 0.4356 | 17.6471 |
68
- | 0.0414 | 10.0 | 220 | 0.4186 | 17.8105 |
69
- | 0.027 | 11.0 | 242 | 0.4105 | 17.3203 |
70
- | 0.0249 | 12.0 | 264 | 0.4037 | 16.9935 |
71
- | 0.0314 | 13.0 | 286 | 0.4077 | 17.3203 |
72
- | 0.0214 | 14.0 | 308 | 0.4085 | 17.6471 |
73
- | 0.0148 | 15.0 | 330 | 0.4085 | 17.6471 |
74
 
75
 
76
  ### Framework versions
 
1
  ---
2
  library_name: transformers
 
 
3
  license: apache-2.0
4
  base_model: openai/whisper-small
5
  tags:
 
7
  metrics:
8
  - wer
9
  model-index:
10
+ - name: 52Hz-small-fr-v3
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # 52Hz-small-fr-v3
18
 
19
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4065
22
+ - Wer: 17.8105
23
 
24
  ## Model description
25
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer |
56
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
57
+ | 1.4611 | 1.0 | 22 | 0.8947 | 39.8693 |
58
+ | 0.6451 | 2.0 | 44 | 0.5211 | 25.4902 |
59
+ | 0.3082 | 3.0 | 66 | 0.4803 | 20.4248 |
60
+ | 0.224 | 4.0 | 88 | 0.4255 | 37.7451 |
61
+ | 0.1531 | 5.0 | 110 | 0.4062 | 17.9739 |
62
+ | 0.1294 | 6.0 | 132 | 0.4146 | 19.1176 |
63
+ | 0.1018 | 7.0 | 154 | 0.4123 | 19.6078 |
64
+ | 0.0546 | 8.0 | 176 | 0.4034 | 20.2614 |
65
+ | 0.0401 | 9.0 | 198 | 0.4386 | 17.3203 |
66
+ | 0.0476 | 10.0 | 220 | 0.4225 | 18.6275 |
67
+ | 0.0261 | 11.0 | 242 | 0.4131 | 18.4641 |
68
+ | 0.0226 | 12.0 | 264 | 0.4035 | 17.8105 |
69
+ | 0.0323 | 13.0 | 286 | 0.4050 | 17.6471 |
70
+ | 0.0208 | 14.0 | 308 | 0.4064 | 17.8105 |
71
+ | 0.0189 | 15.0 | 330 | 0.4065 | 17.8105 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:025a086addf73284bc62293c338f154796e70520cc261c5707ff5e342a8a75e4
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8696bb7a006d64e21429f7da39064a434adef7f492203854bbf49e64bfa5459a
3
  size 966995080
runs/Feb18_19-01-02_sl-tp-br-517/events.out.tfevents.1771437664.sl-tp-br-517.2580079.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfdf3f877879c7aedeb142561d36be3812e35fd4c2780958ec7466c612c8d0b7
3
- size 25325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b11f099e5cd9ca1ff4ef855b01f83df9a1a3ce201044c898efdaeec2ae5ce6d
3
+ size 25679