Hugging Face's logo

akhikhan123
/
xlsr-wav2vec2-model

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
akhikhan123 commited on
Commit
9d1171d
·
verified ·
1 Parent(s): 5ddc618

End of training

Browse files
Files changed (4) hide show
  1. README.md +16 -17
  2. model.safetensors +1 -1
  3. runs/May15_18-22-50_1a7ed9523d40/events.out.tfevents.1715797440.1a7ed9523d40.1927.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: facebook/wav2vec2-xls-r-300m
6
  metrics:
7
  - wer
8
  model-index:
@@ -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-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7290
21
- - Wer: 0.4124
22
 
23
  ## Model description
24
 
@@ -45,25 +45,24 @@ The following hyperparameters were used during training:
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
  - num_epochs: 30
48
- - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-------:|:----:|:---------------:|:------:|
54
- | 7.6084 | 2.1552 | 500 | 3.5347 | 0.9779 |
55
- | 2.9101 | 4.3103 | 1000 | 3.0371 | 0.9779 |
56
- | 1.9452 | 6.4655 | 1500 | 0.9591 | 0.7081 |
57
- | 0.9155 | 8.6207 | 2000 | 0.7387 | 0.5667 |
58
- | 0.6076 | 10.7759 | 2500 | 0.6607 | 0.5046 |
59
- | 0.461 | 12.9310 | 3000 | 0.5965 | 0.4689 |
60
- | 0.3687 | 15.0862 | 3500 | 0.6324 | 0.4639 |
61
- | 0.2981 | 17.2414 | 4000 | 0.6604 | 0.4617 |
62
- | 0.26 | 19.3966 | 4500 | 0.6835 | 0.4538 |
63
- | 0.2247 | 21.5517 | 5000 | 0.6830 | 0.4304 |
64
- | 0.1959 | 23.7069 | 5500 | 0.6905 | 0.4285 |
65
- | 0.1769 | 25.8621 | 6000 | 0.7278 | 0.4254 |
66
- | 0.1483 | 28.0172 | 6500 | 0.7290 | 0.4124 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
  tags:
5
  - generated_from_trainer
 
6
  metrics:
7
  - wer
8
  model-index:
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.8086
21
+ - Wer: 0.4364
22
 
23
  ## Model description
24
 
 
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
  - num_epochs: 30
 
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-------:|:----:|:---------------:|:------:|
53
+ | 7.4037 | 2.1645 | 500 | 3.5799 | 1.0 |
54
+ | 2.9066 | 4.3290 | 1000 | 3.0843 | 1.0 |
55
+ | 2.1161 | 6.4935 | 1500 | 1.1052 | 0.7927 |
56
+ | 1.0022 | 8.6580 | 2000 | 0.7942 | 0.6240 |
57
+ | 0.6621 | 10.8225 | 2500 | 0.7538 | 0.5438 |
58
+ | 0.5084 | 12.9870 | 3000 | 0.6946 | 0.5070 |
59
+ | 0.3937 | 15.1515 | 3500 | 0.7098 | 0.4751 |
60
+ | 0.3267 | 17.3160 | 4000 | 0.7231 | 0.4620 |
61
+ | 0.2675 | 19.4805 | 4500 | 0.7481 | 0.4604 |
62
+ | 0.2308 | 21.6450 | 5000 | 0.7755 | 0.4594 |
63
+ | 0.199 | 23.8095 | 5500 | 0.7615 | 0.4438 |
64
+ | 0.1803 | 25.9740 | 6000 | 0.8217 | 0.4358 |
65
+ | 0.1599 | 28.1385 | 6500 | 0.8086 | 0.4364 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de399986abca785545b05f5b0935f4f9358c5e95714575063e1225a83bbb6750
3
  size 1261938680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9980276158aba611a8bac6f33024a1e8a7dddd6bcb8faf8a3c0b5d8bc62ecfdb
3
  size 1261938680
runs/May15_18-22-50_1a7ed9523d40/events.out.tfevents.1715797440.1a7ed9523d40.1927.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d45ac2a41927f7962d6081e7eaa3efd98633e0bdbb4eb96b6fb59e77c556c0d
3
+ size 13392
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63019ea26818b45657c886c12d23f70c0dbf7fb79f5eb96a1e367002c2bac0ec
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47006c9fec29756839b149ed790cf029600505b85031597f461569b12fb5ddb0
3
  size 4984