Hugging Face's logo

ylacombe
/
w2v-bert-2.0-mongolian-colab-CV16.0

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
ylacombe HF staff commited on
Commit
5b76dde
•
1 Parent(s): ba4725c

End of training

Browse files
Files changed (3) hide show
  1. README.md +8 -8
  2. model.safetensors +1 -1
  3. runs/Jan24_18-32-56_6e4cc44dd1fe/events.out.tfevents.1706121269.6e4cc44dd1fe.1189.0 +2 -2
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 0.32401566238851426
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the common_voice_16_0 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.5288
35
- - Wer: 0.3240
36
 
37
  ## Model description
38
 
@@ -67,10 +67,10 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | 1.7127 | 2.37 | 300 | 0.6477 | 0.5179 |
71
- | 0.3493 | 4.74 | 600 | 0.6158 | 0.4420 |
72
- | 0.1805 | 7.11 | 900 | 0.5251 | 0.3673 |
73
- | 0.0754 | 9.49 | 1200 | 0.5288 | 0.3240 |
74
 
75
 
76
  ### Framework versions
@@ -78,4 +78,4 @@ The following hyperparameters were used during training:
78
  - Transformers 4.37.0.dev0
79
  - Pytorch 2.1.0+cu121
80
  - Datasets 2.16.1
81
- - Tokenizers 0.15.0
 
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 0.3382089065303681
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the common_voice_16_0 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.5279
35
+ - Wer: 0.3382
36
 
37
  ## Model description
38
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 2.0592 | 2.37 | 300 | 0.7052 | 0.5907 |
71
+ | 0.3893 | 4.74 | 600 | 0.5848 | 0.4508 |
72
+ | 0.1926 | 7.11 | 900 | 0.5277 | 0.3830 |
73
+ | 0.0857 | 9.49 | 1200 | 0.5279 | 0.3382 |
74
 
75
 
76
  ### Framework versions
 
78
  - Transformers 4.37.0.dev0
79
  - Pytorch 2.1.0+cu121
80
  - Datasets 2.16.1
81
+ - Tokenizers 0.15.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64d08554453625b4e175f480469ef063227aa808a369b8a87473ea8c4492abe2
3
  size 2423122060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df3ddfec72be5ae4e566056df96573a39ed89fe29e9bee18168c540f32863147
3
  size 2423122060
runs/Jan24_18-32-56_6e4cc44dd1fe/events.out.tfevents.1706121269.6e4cc44dd1fe.1189.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e9d7d8fa4df0ed7b6dce9cc5ed9f8c87a235916dd02adbe7cbb031a2fc82263
3
- size 7575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed95f8e2ba9a5f0ed7786441b92ab4f906a9af007017378915d1cca26e02d4df
3
+ size 7929