Hugging Face's logo

macarious
/
torgo_xlsr_finetune_M01_old

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
macarious commited on
Commit
5a8041a
•
1 Parent(s): 80e27b9

Training in progress, step 22500

Browse files
Files changed (6) hide show
  1. .gitattributes +2 -0
  2. README.md +7 -35
  3. pytorch_model.bin +1 -1
  4. runs/Jan25_00-36-00_d1005/1706161084.7326531/events.out.tfevents.1706161084.d1005.11790.1 +3 -0
  5. runs/Jan25_00-36-00_d1005/events.out.tfevents.1706161084.d1005.11790.0 +3 -0
  6. training_args.bin +1 -1
.gitattributes CHANGED
@@ -8,3 +8,5 @@ runs/Nov20_19-57-17_0f53531ac0df/events.out.tfevents.1700510385.0f53531ac0df.526
8
  runs/Nov20_19-57-17_0f53531ac0df/1700535469.8101287/events.out.tfevents.1700535469.0f53531ac0df.52655.2 filter=lfs diff=lfs merge=lfs -text
9
  runs/Jan24_17-40-23_d1005/1706136138.9474404/events.out.tfevents.1706136138.d1005.108367.1 filter=lfs diff=lfs merge=lfs -text
10
  runs/Jan24_17-40-23_d1005/events.out.tfevents.1706136138.d1005.108367.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
8
  runs/Nov20_19-57-17_0f53531ac0df/1700535469.8101287/events.out.tfevents.1700535469.0f53531ac0df.52655.2 filter=lfs diff=lfs merge=lfs -text
9
  runs/Jan24_17-40-23_d1005/1706136138.9474404/events.out.tfevents.1706136138.d1005.108367.1 filter=lfs diff=lfs merge=lfs -text
10
  runs/Jan24_17-40-23_d1005/events.out.tfevents.1706136138.d1005.108367.0 filter=lfs diff=lfs merge=lfs -text
11
+ runs/Jan25_00-36-00_d1005/1706161084.7326531/events.out.tfevents.1706161084.d1005.11790.1 filter=lfs diff=lfs merge=lfs -text
12
+ runs/Jan25_00-36-00_d1005/events.out.tfevents.1706161084.d1005.11790.0 filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,9 +1,12 @@
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
 
 
 
4
  - generated_from_trainer
5
- metrics:
6
- - wer
7
  model-index:
8
  - name: torgo_xlsr_finetune_M01
9
  results: []
@@ -14,10 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # torgo_xlsr_finetune_M01
16
 
17
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
18
- It achieves the following results on the evaluation set:
19
- - Loss: 1.6947
20
- - Wer: 0.3181
21
 
22
  ## Model description
23
 
@@ -45,35 +45,7 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 1000
48
- - num_epochs: 20
49
-
50
- ### Training results
51
-
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
- | 3.4346 | 0.89 | 1000 | 3.3570 | 1.0 |
55
- | 1.3708 | 1.79 | 2000 | 1.5774 | 0.7569 |
56
- | 0.7783 | 2.69 | 3000 | 1.6546 | 0.6103 |
57
- | 0.5676 | 3.58 | 4000 | 1.3849 | 0.5216 |
58
- | 0.4476 | 4.48 | 5000 | 1.5294 | 0.5 |
59
- | 0.4264 | 5.37 | 6000 | 1.5832 | 0.4534 |
60
- | 0.3434 | 6.27 | 7000 | 1.4397 | 0.4233 |
61
- | 0.3371 | 7.16 | 8000 | 1.4635 | 0.4129 |
62
- | 0.3268 | 8.06 | 9000 | 1.5989 | 0.3828 |
63
- | 0.2623 | 8.95 | 10000 | 1.5145 | 0.3836 |
64
- | 0.2755 | 9.85 | 11000 | 1.6695 | 0.3569 |
65
- | 0.2304 | 10.74 | 12000 | 1.4313 | 0.3397 |
66
- | 0.2052 | 11.64 | 13000 | 1.4242 | 0.3466 |
67
- | 0.199 | 12.53 | 14000 | 1.7287 | 0.3405 |
68
- | 0.2124 | 13.43 | 15000 | 1.4715 | 0.3086 |
69
- | 0.1858 | 14.32 | 16000 | 1.6835 | 0.3086 |
70
- | 0.1667 | 15.22 | 17000 | 1.6080 | 0.3233 |
71
- | 0.1551 | 16.11 | 18000 | 1.6151 | 0.3293 |
72
- | 0.1638 | 17.01 | 19000 | 1.5014 | 0.3034 |
73
- | 0.1584 | 17.9 | 20000 | 1.7036 | 0.3233 |
74
- | 0.1486 | 18.8 | 21000 | 1.6527 | 0.3207 |
75
- | 0.1337 | 19.7 | 22000 | 1.6947 | 0.3181 |
76
-
77
 
78
  ### Framework versions
79
 
 
1
  ---
2
+ language:
3
+ - en
4
  license: apache-2.0
5
  tags:
6
+ - audio
7
+ - speech
8
+ - wav2vec2
9
  - generated_from_trainer
 
 
10
  model-index:
11
  - name: torgo_xlsr_finetune_M01
12
  results: []
 
17
 
18
  # torgo_xlsr_finetune_M01
19
 
20
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the torgo dataset.
 
 
 
21
 
22
  ## Model description
23
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 1000
48
+ - num_epochs: 40
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
 
50
  ### Framework versions
51
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47c0461f3810d44e7bbbf07b0515095a31c5673c2ba08752b7a7b9e35550c402
3
  size 1262033514
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc724dae5e43065c34ef9c4367b41a5bee44e29f510eaa329207495eedc140d
3
  size 1262033514
runs/Jan25_00-36-00_d1005/1706161084.7326531/events.out.tfevents.1706161084.d1005.11790.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78dd6a5044a7d0efcc683625b8eec1f8478553fc4cbf354b23918dbeb009bbae
3
+ size 5793
runs/Jan25_00-36-00_d1005/events.out.tfevents.1706161084.d1005.11790.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1686e976e75b043f8ee108330a75fba55c3c5d94dad7b88d6136815fdf265ce
3
+ size 5742
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5d5d6f24836711d68d3b58cc46f9a3f12a855f440dc6b723f3b2f031ce7b515
3
  size 3960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049dfce55df8207c33567defa32e73ba7ec4891ebe7fcc0f67d5df35f894047c
3
  size 3960