Hugging Face's logo

Asim037
/
wav222vec222v2-stt

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
wav2vec2
[finetuned_model, lj_speech11]
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Asim037 commited on
Commit
08e6df9
•
1 Parent(s): ac3f1d8

End of training

Browse files
Files changed (5) hide show
  1. README.md +16 -12
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Jun19_11-34-23_fcf1e22c2e2d/events.out.tfevents.1718796905.fcf1e22c2e2d.214.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -2,10 +2,10 @@
2
  language:
3
  - eng
4
  license: apache-2.0
 
5
  tags:
6
  - '[finetuned_model, lj_speech11]'
7
  - generated_from_trainer
8
- base_model: facebook/wav2vec2-base-960h
9
  datasets:
10
  - FYP/LJ-SpeechLJ
11
  model-index:
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the Lj-Speech dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 310.7488
24
 
25
  ## Model description
26
 
@@ -55,20 +55,24 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:----:|:---------------:|
58
- | 3527.1737 | 0.5362 | 50 | 433.5859 |
59
- | 441.3472 | 1.0724 | 100 | 331.3980 |
60
- | 404.9114 | 1.6086 | 150 | 379.2116 |
61
- | 330.0151 | 2.1448 | 200 | 319.7489 |
62
- | 346.7672 | 2.6810 | 250 | 307.3814 |
63
- | 398.5639 | 3.2172 | 300 | 349.2720 |
64
- | 331.2473 | 3.7534 | 350 | 308.0336 |
65
- | 311.4908 | 4.2895 | 400 | 306.9877 |
66
- | 312.0619 | 4.8257 | 450 | 310.7488 |
 
 
 
 
67
 
68
 
69
  ### Framework versions
70
 
71
  - Transformers 4.41.2
72
  - Pytorch 2.3.0+cu121
73
- - Datasets 2.19.2
74
  - Tokenizers 0.19.1
 
2
  language:
3
  - eng
4
  license: apache-2.0
5
+ base_model: facebook/wav2vec2-base-960h
6
  tags:
7
  - '[finetuned_model, lj_speech11]'
8
  - generated_from_trainer
 
9
  datasets:
10
  - FYP/LJ-SpeechLJ
11
  model-index:
 
20
 
21
  This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the Lj-Speech dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 491.2500
24
 
25
  ## Model description
26
 
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss |
57
  |:-------------:|:------:|:----:|:---------------:|
58
+ | 494.9709 | 0.3795 | 50 | 486.0701 |
59
+ | 534.2352 | 0.7590 | 100 | 488.7172 |
60
+ | 816.0739 | 1.1385 | 150 | 490.4418 |
61
+ | 566.1295 | 1.5180 | 200 | 504.5211 |
62
+ | 586.0909 | 1.8975 | 250 | 489.5141 |
63
+ | 601.5043 | 2.2770 | 300 | 486.6875 |
64
+ | 487.8737 | 2.6565 | 350 | 489.5807 |
65
+ | 1145.4591 | 3.0361 | 400 | 511.4276 |
66
+ | 686.6008 | 3.4156 | 450 | 496.0722 |
67
+ | 664.612 | 3.7951 | 500 | 486.9992 |
68
+ | 630.4309 | 4.1746 | 550 | 500.0555 |
69
+ | 513.7977 | 4.5541 | 600 | 488.6891 |
70
+ | 494.3428 | 4.9336 | 650 | 491.2500 |
71
 
72
 
73
  ### Framework versions
74
 
75
  - Transformers 4.41.2
76
  - Pytorch 2.3.0+cu121
77
+ - Datasets 2.20.0
78
  - Tokenizers 0.19.1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "facebook/wav2vec2-large-960h",
3
  "activation_dropout": 0.1,
4
  "adapter_attn_dim": null,
5
  "adapter_kernel_size": 3,
 
1
  {
2
+ "_name_or_path": "Asim037/wav222vec222v2-stt",
3
  "activation_dropout": 0.1,
4
  "adapter_attn_dim": null,
5
  "adapter_kernel_size": 3,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b4c6cd1fab1e35225d9860bf068ebb26b53b549a3a2e29227dcfc38a645f379
3
  size 1261897368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e94557e9d556c3d3d4a334f29f7af74c9e1d4f82bd00baaf0ca1640a444e5db
3
  size 1261897368
runs/Jun19_11-34-23_fcf1e22c2e2d/events.out.tfevents.1718796905.fcf1e22c2e2d.214.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ab54f6893a6648f2c71fc67f0aa91c7844be33a570bf8418d5ffa9678d77f0
3
+ size 15587
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b38fea795393cd8daac4803951808a6d9d9d3a5cfdcc5861354689506cb98b8f
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac07d2b3e831b8c6f108ef93fcd1acdc00de6998393aff05ef2fed0bf34bdc65
3
  size 5112