Hugging Face's logo

Bernadette16
/
ft-wav2vec2-with-minds-asr

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
Bernadette16 commited on
Commit
b254e28
•
1 Parent(s): c4c6c6a

End of training

Browse files
Files changed (3) hide show
  1. README.md +22 -11
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
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 PolyAI/minds14 dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 14.6779
21
- - Wer: 0.9992
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 1e-05
41
  - train_batch_size: 1
42
  - eval_batch_size: 1
43
  - seed: 42
@@ -45,18 +45,29 @@ The following hyperparameters were used during training:
45
  - total_train_batch_size: 4
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 40
49
- - training_steps: 80
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Wer |
55
- |:-------------:|:-----:|:----:|:---------------:|:------:|
56
- | No log | 0.2 | 20 | 18.3455 | 1.0 |
57
- | 22.3132 | 0.4 | 40 | 14.6779 | 0.9992 |
58
- | 12.9314 | 0.6 | 60 | 5.6604 | 1.0 |
59
- | 12.9314 | 0.8 | 80 | 3.8006 | 1.0 |
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the PolyAI/minds14 dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.3474
21
+ - Wer: 1.0
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
  - train_batch_size: 1
42
  - eval_batch_size: 1
43
  - seed: 42
 
45
  - total_train_batch_size: 4
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 20
49
+ - training_steps: 0
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
55
+ |:-------------:|:-----:|:----:|:---------------:|:---:|
56
+ | No log | 0.2 | 20 | 11.2889 | 1.0 |
57
+ | 15.8315 | 0.4 | 40 | 3.3474 | 1.0 |
58
+ | 3.4511 | 0.6 | 60 | 3.1646 | 1.0 |
59
+ | 3.4511 | 0.8 | 80 | 3.1071 | 1.0 |
60
+ | 3.1703 | 1.0 | 100 | 3.0801 | 1.0 |
61
+ | 3.1056 | 1.2 | 120 | 3.0708 | 1.0 |
62
+ | 3.1056 | 1.4 | 140 | 3.0602 | 1.0 |
63
+ | 3.0782 | 1.6 | 160 | 3.0469 | 1.0 |
64
+ | 3.0491 | 1.8 | 180 | 3.0536 | 1.0 |
65
+ | 3.0491 | 2.0 | 200 | 3.0506 | 1.0 |
66
+ | 3.262 | 2.2 | 220 | 3.0482 | 1.0 |
67
+ | 3.0506 | 2.4 | 240 | 3.0418 | 1.0 |
68
+ | 3.0506 | 2.6 | 260 | 3.0357 | 1.0 |
69
+ | 3.1029 | 2.8 | 280 | 3.0308 | 1.0 |
70
+ | 3.0059 | 3.0 | 300 | 3.0351 | 1.0 |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44ee873a2e1a04033fd997928a72b608d4fe19176b2bb11f8ac1ed2d308caf38
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c3a4bfe71733e01fbd6945882d6cba50798079bff60673cb81e186a3fcadc13
3
  size 377611120
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e3cca9e3411a56b32081dfe18c164bcc86831a3e5c4d47f97cc41d9d07493b5
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c06f357c765d4e4ff3967c56711fa7028a1fe26ce8abc49d915ad56f2593c19
3
  size 4600