Seynabou commited on
Commit
fbe3c8f
·
verified ·
1 Parent(s): f45edfe

End of training

Browse files
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 73.49819331526649
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [cifope/whisper-small-wolof](https://huggingface.co/cifope/whisper-small-wolof) on the fleurs dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 1.6066
36
- - Wer: 73.4982
37
 
38
  ## Model description
39
 
@@ -61,15 +61,14 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
- - training_steps: 100
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
71
- | 2.4692 | 1.4 | 50 | 2.1379 | 77.2358 |
72
- | 1.7299 | 2.8 | 100 | 1.6066 | 73.4982 |
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 64.97289972899729
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [cifope/whisper-small-wolof](https://huggingface.co/cifope/whisper-small-wolof) on the fleurs dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 1.5332
36
+ - Wer: 64.9729
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_steps: 500
64
+ - training_steps: 50
65
  - mixed_precision_training: Native AMP
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
71
+ | 1.4814 | 1.4 | 50 | 1.5332 | 64.9729 |
 
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ea27a42b4bda4dc1f6f2385b861f9820635ad2e68e6fed4ae31dad3c1294dcc
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3eff38b887f782a0e60842f1cd7750d66ab16c570b0a726cff9d933903d449b
3
  size 966995080
runs/Jan28_02-56-05_7018d94f3010/events.out.tfevents.1706410566.7018d94f3010.3945.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5f3908816dad9110f0a52bf31b6b6e1c43e1a3630f44475d6951236ea38553
3
+ size 6025
special_tokens_map.json CHANGED
@@ -125,7 +125,7 @@
125
  "pad_token": {
126
  "content": "<|endoftext|>",
127
  "lstrip": false,
128
- "normalized": false,
129
  "rstrip": false,
130
  "single_word": false
131
  },
 
125
  "pad_token": {
126
  "content": "<|endoftext|>",
127
  "lstrip": false,
128
+ "normalized": true,
129
  "rstrip": false,
130
  "single_word": false
131
  },
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbf4fd3b523dfb9f05d769ec28b71be0a9697cf27b56d7da0e191f487af8a27d
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add449b6b45c062577fa4cbb8213c91b2aec69c029d543a25382416e4c0730e7
3
  size 4728