Hugging Face's logo

httpschiara
/
my_awesome_asr_mind_model

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
httpschiara commited on
Commit
a60a279
•
1 Parent(s): 8a21a63

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -8
  2. model.safetensors +1 -1
  3. runs/May24_16-09-18_b53f148b66a1/events.out.tfevents.1716566967.b53f148b66a1.569.3 +2 -2
README.md CHANGED
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 12.5233
36
  - Wer: 1.0
37
 
38
  ## Model description
@@ -54,22 +54,24 @@ More information needed
54
  The following hyperparameters were used during training:
55
  - learning_rate: 1e-05
56
  - train_batch_size: 4
57
- - eval_batch_size: 4
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
  - total_train_batch_size: 8
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - num_epochs: 3
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Wer |
69
- |:-------------:|:-----:|:----:|:---------------:|:------:|
70
- | No log | 1.0 | 19 | 36.1883 | 1.0 |
71
- | No log | 2.0 | 38 | 19.2765 | 0.9985 |
72
- | No log | 3.0 | 57 | 12.5233 | 1.0 |
 
 
73
 
74
 
75
  ### Framework versions
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the minds14 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 4.0528
36
  - Wer: 1.0
37
 
38
  ## Model description
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 1e-05
56
  - train_batch_size: 4
57
+ - eval_batch_size: 5
58
  - seed: 42
59
  - gradient_accumulation_steps: 2
60
  - total_train_batch_size: 8
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
+ - num_epochs: 5
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
70
+ | 18.1868 | 1.0 | 19 | 11.4282 | 1.0 |
71
+ | 8.8369 | 2.0 | 38 | 5.3475 | 1.0 |
72
+ | 5.1229 | 3.0 | 57 | 4.3310 | 1.0 |
73
+ | 4.8009 | 4.0 | 76 | 4.1192 | 1.0 |
74
+ | 4.6396 | 5.0 | 95 | 4.0528 | 1.0 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c110fe5085a4263900ae12e98b8fbb7afceb53ed6b69840ce907e428547fdaf
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b50ea542db0004883aa5b0cb11976b8b61f3bbdc33e698ad408d9c96c9fb48f0
3
  size 377611120
runs/May24_16-09-18_b53f148b66a1/events.out.tfevents.1716566967.b53f148b66a1.569.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4b96ddb3ecc8018097c0ce87d03af08126b33d52d08161b167b118e33fb877d
3
- size 9146
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:222f500dcc9d38181bb7ec5b5e23ef2e8e9033230fdc8052880785613e740b85
3
+ size 9494