Hugging Face's logo

PolyChirag
/
Marathi_ASR_using_xlsr_wav2vec

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
PolyChirag commited on
Commit
634de2c
•
1 Parent(s): 44e6710

End of training

Browse files
Files changed (3) hide show
  1. README.md +16 -9
  2. model.safetensors +1 -1
  3. runs/Apr21_12-15-16_74b57a095dc9/events.out.tfevents.1713701881.74b57a095dc9.34.1 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.787176724137931
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.7676
36
- - Wer: 0.7872
37
 
38
  ## Model description
39
 
@@ -52,15 +52,13 @@ More information needed
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
- - learning_rate: 0.0003
56
  - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
59
- - gradient_accumulation_steps: 2
60
- - total_train_batch_size: 32
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
- - lr_scheduler_warmup_steps: 500
64
  - num_epochs: 30
65
  - mixed_precision_training: Native AMP
66
 
@@ -68,8 +66,17 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:-------:|:----:|:---------------:|:------:|
71
- | 6.5921 | 10.6667 | 400 | 3.3151 | 1.0021 |
72
- | 2.0358 | 21.3333 | 800 | 0.7676 | 0.7872 |
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.7180765086206896
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.7582
36
+ - Wer: 0.7181
37
 
38
  ## Model description
39
 
 
52
  ### Training hyperparameters
53
 
54
  The following hyperparameters were used during training:
55
+ - learning_rate: 1e-05
56
  - train_batch_size: 16
57
  - eval_batch_size: 8
58
  - seed: 42
 
 
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 300
62
  - num_epochs: 30
63
  - mixed_precision_training: Native AMP
64
 
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer |
68
  |:-------------:|:-------:|:----:|:---------------:|:------:|
69
+ | No log | 2.6667 | 200 | 0.7381 | 0.7263 |
70
+ | 0.336 | 5.3333 | 400 | 0.7472 | 0.7289 |
71
+ | 0.336 | 8.0 | 600 | 0.7452 | 0.7215 |
72
+ | 0.3237 | 10.6667 | 800 | 0.7449 | 0.7212 |
73
+ | 0.3237 | 13.3333 | 1000 | 0.7546 | 0.7192 |
74
+ | 0.3104 | 16.0 | 1200 | 0.7565 | 0.7210 |
75
+ | 0.3104 | 18.6667 | 1400 | 0.7550 | 0.7193 |
76
+ | 0.3089 | 21.3333 | 1600 | 0.7551 | 0.7186 |
77
+ | 0.3089 | 24.0 | 1800 | 0.7572 | 0.7185 |
78
+ | 0.2993 | 26.6667 | 2000 | 0.7571 | 0.7175 |
79
+ | 0.2993 | 29.3333 | 2200 | 0.7582 | 0.7181 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71ff0e2eb7c544679e6dcaea0a98fc0b395b5cc60d13c1c621907b9c9eacd6b6
3
  size 1262155980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ba5a0d257542d1e555907159ff0925b9de7419a6030206a64ceb135accc375
3
  size 1262155980
runs/Apr21_12-15-16_74b57a095dc9/events.out.tfevents.1713701881.74b57a095dc9.34.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2141f5314e5d130d50a2da3ed12e0549cd8cd09f4ef86a50dd1ac6e5f91b8827
3
- size 10999
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b93f27e7a147561ff5d330cf274bd874370df0a0ee9e08e30e7731771d0414
3
+ size 11353