Hugging Face's logo

celneo7
/
results

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
celneo7 commited on
Commit
8dd46b9
•
1 Parent(s): 02c1ab7

End of training

Browse files
Files changed (3) hide show
  1. README.md +57 -15
  2. model.safetensors +1 -1
  3. runs/May25_17-58-40_instance-til-team-1/events.out.tfevents.1716660054.instance-til-team-1 +2 -2
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0159
21
- - Wer: 0.4194
22
 
23
  ## Model description
24
 
@@ -45,24 +45,66 @@ The following hyperparameters were used during training:
45
  - total_train_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 1000
49
  - num_epochs: 30
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Wer |
55
- |:-------------:|:-------:|:----:|:---------------:|:------:|
56
- | 4.456 | 2.8571 | 500 | 2.8521 | 1.0 |
57
- | 1.7436 | 5.7143 | 1000 | 0.0950 | 0.5740 |
58
- | 0.0812 | 8.5714 | 1500 | 0.0351 | 0.4816 |
59
- | 0.0377 | 11.4286 | 2000 | 0.0277 | 0.4739 |
60
- | 0.024 | 14.2857 | 2500 | 0.0198 | 0.4397 |
61
- | 0.0181 | 17.1429 | 3000 | 0.0169 | 0.4276 |
62
- | 0.0135 | 20.0 | 3500 | 0.0189 | 0.4276 |
63
- | 0.0102 | 22.8571 | 4000 | 0.0176 | 0.4238 |
64
- | 0.0086 | 25.7143 | 4500 | 0.0153 | 0.4221 |
65
- | 0.0074 | 28.5714 | 5000 | 0.0159 | 0.4194 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.0216
21
+ - Wer: 1.0
22
 
23
  ## Model description
24
 
 
45
  - total_train_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 500
49
  - num_epochs: 30
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-------:|:----:|:---------------:|:---:|
56
+ | 6.0993 | 0.5714 | 100 | 3.1919 | 1.0 |
57
+ | 2.9332 | 1.1429 | 200 | 3.0675 | 1.0 |
58
+ | 2.878 | 1.7143 | 300 | 3.1538 | 1.0 |
59
+ | 2.873 | 2.2857 | 400 | 2.9688 | 1.0 |
60
+ | 2.8574 | 2.8571 | 500 | 3.0386 | 1.0 |
61
+ | 2.859 | 3.4286 | 600 | 3.0947 | 1.0 |
62
+ | 2.8631 | 4.0 | 700 | 3.2471 | 1.0 |
63
+ | 2.8612 | 4.5714 | 800 | 2.9827 | 1.0 |
64
+ | 2.8592 | 5.1429 | 900 | 3.0277 | 1.0 |
65
+ | 2.8617 | 5.7143 | 1000 | 3.1227 | 1.0 |
66
+ | 2.8644 | 6.2857 | 1100 | 3.0502 | 1.0 |
67
+ | 2.8618 | 6.8571 | 1200 | 3.0055 | 1.0 |
68
+ | 2.8638 | 7.4286 | 1300 | 3.0646 | 1.0 |
69
+ | 2.8608 | 8.0 | 1400 | 3.1780 | 1.0 |
70
+ | 2.8585 | 8.5714 | 1500 | 2.9719 | 1.0 |
71
+ | 2.8624 | 9.1429 | 1600 | 3.0521 | 1.0 |
72
+ | 2.8588 | 9.7143 | 1700 | 3.0839 | 1.0 |
73
+ | 2.8594 | 10.2857 | 1800 | 3.1120 | 1.0 |
74
+ | 2.8566 | 10.8571 | 1900 | 2.9648 | 1.0 |
75
+ | 2.8587 | 11.4286 | 2000 | 3.0812 | 1.0 |
76
+ | 2.8588 | 12.0 | 2100 | 3.1690 | 1.0 |
77
+ | 2.8607 | 12.5714 | 2200 | 2.9951 | 1.0 |
78
+ | 2.8561 | 13.1429 | 2300 | 3.0317 | 1.0 |
79
+ | 2.8565 | 13.7143 | 2400 | 3.0880 | 1.0 |
80
+ | 2.8638 | 14.2857 | 2500 | 3.0978 | 1.0 |
81
+ | 2.8563 | 14.8571 | 2600 | 2.9716 | 1.0 |
82
+ | 2.8592 | 15.4286 | 2700 | 3.0461 | 1.0 |
83
+ | 2.859 | 16.0 | 2800 | 3.1339 | 1.0 |
84
+ | 2.8584 | 16.5714 | 2900 | 3.0304 | 1.0 |
85
+ | 2.8562 | 17.1429 | 3000 | 2.9964 | 1.0 |
86
+ | 2.8574 | 17.7143 | 3100 | 3.0665 | 1.0 |
87
+ | 2.8609 | 18.2857 | 3200 | 3.1042 | 1.0 |
88
+ | 2.8564 | 18.8571 | 3300 | 2.9905 | 1.0 |
89
+ | 2.8601 | 19.4286 | 3400 | 3.0030 | 1.0 |
90
+ | 2.8562 | 20.0 | 3500 | 3.1000 | 1.0 |
91
+ | 2.8565 | 20.5714 | 3600 | 3.0409 | 1.0 |
92
+ | 2.8566 | 21.1429 | 3700 | 2.9837 | 1.0 |
93
+ | 2.8577 | 21.7143 | 3800 | 3.0294 | 1.0 |
94
+ | 2.8554 | 22.2857 | 3900 | 3.0737 | 1.0 |
95
+ | 2.854 | 22.8571 | 4000 | 3.0101 | 1.0 |
96
+ | 2.8556 | 23.4286 | 4100 | 3.0014 | 1.0 |
97
+ | 2.8557 | 24.0 | 4200 | 3.0693 | 1.0 |
98
+ | 2.8531 | 24.5714 | 4300 | 3.0308 | 1.0 |
99
+ | 2.8552 | 25.1429 | 4400 | 3.0050 | 1.0 |
100
+ | 2.8536 | 25.7143 | 4500 | 3.0215 | 1.0 |
101
+ | 2.855 | 26.2857 | 4600 | 3.0509 | 1.0 |
102
+ | 2.8513 | 26.8571 | 4700 | 3.0163 | 1.0 |
103
+ | 2.8533 | 27.4286 | 4800 | 3.0170 | 1.0 |
104
+ | 2.8552 | 28.0 | 4900 | 3.0345 | 1.0 |
105
+ | 2.8521 | 28.5714 | 5000 | 3.0259 | 1.0 |
106
+ | 2.8522 | 29.1429 | 5100 | 3.0219 | 1.0 |
107
+ | 2.8543 | 29.7143 | 5200 | 3.0216 | 1.0 |
108
 
109
 
110
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b6442352333703cd591367940246dcd7b4cdd3e299a13bddab431355a9e3740
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac5d036b7c494a4de274abf8ed4d1bf492149c7867635f305a884699a9128ef
3
  size 377611120
runs/May25_17-58-40_instance-til-team-1/events.out.tfevents.1716660054.instance-til-team-1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae70f3c4e0bb849c15b77c7b24247fe33c17226f41adef7b1a9c4eb7de25c5c4
3
- size 33627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00fe1aeda262aad8e6daf07653000330e76358d68a06f8a5f2911773148c3d2
3
+ size 34299