Hugging Face's logo

kartikay101
/
wtimit-base-960h-normal-reduced-learning-rate-all

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kartikay101 commited on
Commit
47c5572
•
1 Parent(s): 98ba8f3

kartikay101/wtimit-base-960h-normal-reduced-learning-rate-all

Browse files
Files changed (4) hide show
  1. README.md +15 -24
  2. model.safetensors +1 -1
  3. runs/Jun10_18-11-37_9d8aa697408e/events.out.tfevents.1718043215.9d8aa697408e.1585.2 +3 -0
  4. 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-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3222
21
- - Wer: 0.2108
22
 
23
  ## Model description
24
 
@@ -37,38 +37,29 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-06
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
- - num_epochs: 40
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Wer |
53
- |:-------------:|:-------:|:-----:|:---------------:|:------:|
54
- | 0.4825 | 2.1552 | 1000 | 0.3219 | 0.2605 |
55
- | 0.3671 | 4.3103 | 2000 | 0.3040 | 0.2347 |
56
- | 0.316 | 6.4655 | 3000 | 0.2995 | 0.2291 |
57
- | 0.27 | 8.6207 | 4000 | 0.2990 | 0.2218 |
58
- | 0.2532 | 10.7759 | 5000 | 0.2991 | 0.2210 |
59
- | 0.2402 | 12.9310 | 6000 | 0.2964 | 0.2193 |
60
- | 0.2301 | 15.0862 | 7000 | 0.2992 | 0.2143 |
61
- | 0.216 | 17.2414 | 8000 | 0.3101 | 0.2187 |
62
- | 0.2023 | 19.3966 | 9000 | 0.3122 | 0.2175 |
63
- | 0.1903 | 21.5517 | 10000 | 0.3084 | 0.2155 |
64
- | 0.1898 | 23.7069 | 11000 | 0.3067 | 0.2126 |
65
- | 0.1854 | 25.8621 | 12000 | 0.3114 | 0.2126 |
66
- | 0.1805 | 28.0172 | 13000 | 0.3117 | 0.2118 |
67
- | 0.1679 | 30.1724 | 14000 | 0.3187 | 0.2135 |
68
- | 0.1749 | 32.3276 | 15000 | 0.3195 | 0.2126 |
69
- | 0.1658 | 34.4828 | 16000 | 0.3229 | 0.2110 |
70
- | 0.1641 | 36.6379 | 17000 | 0.3235 | 0.2129 |
71
- | 0.1656 | 38.7931 | 18000 | 0.3222 | 0.2108 |
72
 
73
 
74
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3181
21
+ - Wer: 0.2132
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
+ - num_epochs: 20
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:-------:|:----:|:---------------:|:------:|
54
+ | 0.4297 | 2.1552 | 1000 | 0.3046 | 0.2440 |
55
+ | 0.3137 | 4.3103 | 2000 | 0.2941 | 0.2240 |
56
+ | 0.2578 | 6.4655 | 3000 | 0.2982 | 0.2176 |
57
+ | 0.2153 | 8.6207 | 4000 | 0.3063 | 0.2166 |
58
+ | 0.1998 | 10.7759 | 5000 | 0.3036 | 0.2155 |
59
+ | 0.1913 | 12.9310 | 6000 | 0.3049 | 0.2122 |
60
+ | 0.1836 | 15.0862 | 7000 | 0.3160 | 0.2161 |
61
+ | 0.1755 | 17.2414 | 8000 | 0.3192 | 0.2152 |
62
+ | 0.1681 | 19.3966 | 9000 | 0.3181 | 0.2132 |
 
 
 
 
 
 
 
 
 
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b58687502fb93578b501c1423a2f0ff8045ae8b77a45cef0c6ecf063700dfb0
3
  size 377611120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f237d54409e7a3c8234e7b45d9dfdd17cfb5e1983448efc3cce153ddc6fb91
3
  size 377611120
runs/Jun10_18-11-37_9d8aa697408e/events.out.tfevents.1718043215.9d8aa697408e.1585.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216a363b27d078c61d66843f4b23c0de568006593ae725d2ba6ddf9e8e97af64
3
+ size 13403
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d5265b37c3de57b4ffb799e3cbbf6469f6a6d059d2a0df9ead5da66371b8d13
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29b9333db731c5b8a41aef50d26f350af2a26d9ea72b3b0ce2c474227956978b
3
  size 5176