Hugging Face's logo

Lasion
/
wav2vec2-xls-r-300m-vivos

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Lasion commited on
Commit
9092d22
·
verified ·
1 Parent(s): 3593fdc

End of training

Browse files
Files changed (5) hide show
  1. README.md +50 -50
  2. config.json +2 -2
  3. model.safetensors +2 -2
  4. runs/May13_16-27-39_4434df775738/events.out.tfevents.1715617851.4434df775738.23.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -1,24 +1,24 @@
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:
9
- - name: wav2vec2-base-vivos
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- # wav2vec2-base-vivos
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: 0.5366
21
- - Wer: 0.3320
22
 
23
  ## Model description
24
 
@@ -51,51 +51,51 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
- | 7.987 | 0.66 | 500 | 3.5460 | 1.0 |
55
- | 3.4026 | 1.31 | 1000 | 3.0685 | 1.0 |
56
- | 1.6402 | 1.97 | 1500 | 0.7959 | 0.7082 |
57
- | 0.8229 | 2.62 | 2000 | 0.5581 | 0.5326 |
58
- | 0.6392 | 3.28 | 2500 | 0.4779 | 0.4738 |
59
- | 0.5532 | 3.94 | 3000 | 0.4415 | 0.4491 |
60
- | 0.4937 | 4.59 | 3500 | 0.4318 | 0.4312 |
61
- | 0.4506 | 5.25 | 4000 | 0.4284 | 0.4134 |
62
- | 0.4099 | 5.91 | 4500 | 0.4405 | 0.4267 |
63
- | 0.3848 | 6.56 | 5000 | 0.4097 | 0.3987 |
64
- | 0.3683 | 7.22 | 5500 | 0.4239 | 0.4031 |
65
- | 0.3485 | 7.87 | 6000 | 0.4383 | 0.3926 |
66
- | 0.3313 | 8.53 | 6500 | 0.4779 | 0.3846 |
67
- | 0.321 | 9.19 | 7000 | 0.4623 | 0.3895 |
68
- | 0.3058 | 9.84 | 7500 | 0.4668 | 0.3906 |
69
- | 0.2869 | 10.5 | 8000 | 0.4817 | 0.3749 |
70
- | 0.2828 | 11.15 | 8500 | 0.4777 | 0.3789 |
71
- | 0.2724 | 11.81 | 9000 | 0.4915 | 0.3649 |
72
- | 0.2527 | 12.47 | 9500 | 0.4671 | 0.3670 |
73
- | 0.2588 | 13.12 | 10000 | 0.4693 | 0.3612 |
74
- | 0.2405 | 13.78 | 10500 | 0.4375 | 0.3579 |
75
- | 0.2409 | 14.44 | 11000 | 0.4643 | 0.3595 |
76
- | 0.2247 | 15.09 | 11500 | 0.5445 | 0.3626 |
77
- | 0.2257 | 15.75 | 12000 | 0.4474 | 0.3513 |
78
- | 0.2101 | 16.4 | 12500 | 0.4327 | 0.3502 |
79
- | 0.2118 | 17.06 | 13000 | 0.4830 | 0.3534 |
80
- | 0.1991 | 17.72 | 13500 | 0.4832 | 0.3454 |
81
- | 0.193 | 18.37 | 14000 | 0.4878 | 0.3547 |
82
- | 0.1909 | 19.03 | 14500 | 0.4777 | 0.3506 |
83
- | 0.1869 | 19.69 | 15000 | 0.4722 | 0.3455 |
84
- | 0.1801 | 20.34 | 15500 | 0.4891 | 0.3477 |
85
- | 0.1749 | 21.0 | 16000 | 0.5065 | 0.3446 |
86
- | 0.1715 | 21.65 | 16500 | 0.5381 | 0.3447 |
87
- | 0.1669 | 22.31 | 17000 | 0.4946 | 0.3459 |
88
- | 0.1674 | 22.97 | 17500 | 0.4968 | 0.3425 |
89
- | 0.1579 | 23.62 | 18000 | 0.5210 | 0.3370 |
90
- | 0.1566 | 24.28 | 18500 | 0.5318 | 0.3385 |
91
- | 0.1565 | 24.93 | 19000 | 0.4959 | 0.3381 |
92
- | 0.1517 | 25.59 | 19500 | 0.5181 | 0.3393 |
93
- | 0.1452 | 26.25 | 20000 | 0.5222 | 0.3359 |
94
- | 0.1419 | 26.9 | 20500 | 0.5316 | 0.3333 |
95
- | 0.1389 | 27.56 | 21000 | 0.5094 | 0.3302 |
96
- | 0.1422 | 28.22 | 21500 | 0.5327 | 0.3346 |
97
- | 0.1365 | 28.87 | 22000 | 0.5436 | 0.3320 |
98
- | 0.1337 | 29.53 | 22500 | 0.5366 | 0.3320 |
99
 
100
 
101
  ### 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:
9
+ - name: wav2vec2-xls-r-300m-vivos
10
  results: []
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
+ # wav2vec2-xls-r-300m-vivos
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: 0.5156
21
+ - Wer: 0.3337
22
 
23
  ## Model description
24
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
54
+ | 8.3411 | 0.66 | 500 | 3.5728 | 1.0 |
55
+ | 3.418 | 1.31 | 1000 | 3.1432 | 1.0 |
56
+ | 1.6726 | 1.97 | 1500 | 0.7995 | 0.7146 |
57
+ | 0.8244 | 2.62 | 2000 | 0.5569 | 0.5370 |
58
+ | 0.6392 | 3.28 | 2500 | 0.4773 | 0.4744 |
59
+ | 0.5537 | 3.94 | 3000 | 0.4592 | 0.4631 |
60
+ | 0.4956 | 4.59 | 3500 | 0.4649 | 0.4536 |
61
+ | 0.4539 | 5.25 | 4000 | 0.4345 | 0.4175 |
62
+ | 0.4144 | 5.91 | 4500 | 0.4291 | 0.4204 |
63
+ | 0.3899 | 6.56 | 5000 | 0.4325 | 0.4105 |
64
+ | 0.3748 | 7.22 | 5500 | 0.4151 | 0.3954 |
65
+ | 0.3543 | 7.87 | 6000 | 0.4320 | 0.4070 |
66
+ | 0.3335 | 8.53 | 6500 | 0.4061 | 0.3776 |
67
+ | 0.3266 | 9.19 | 7000 | 0.4307 | 0.3899 |
68
+ | 0.3107 | 9.84 | 7500 | 0.4404 | 0.3866 |
69
+ | 0.2886 | 10.5 | 8000 | 0.4528 | 0.3825 |
70
+ | 0.2897 | 11.15 | 8500 | 0.4027 | 0.3731 |
71
+ | 0.2757 | 11.81 | 9000 | 0.4423 | 0.3837 |
72
+ | 0.2582 | 12.47 | 9500 | 0.4412 | 0.3717 |
73
+ | 0.2598 | 13.12 | 10000 | 0.4410 | 0.3609 |
74
+ | 0.2421 | 13.78 | 10500 | 0.4398 | 0.3651 |
75
+ | 0.2414 | 14.44 | 11000 | 0.4488 | 0.3585 |
76
+ | 0.2259 | 15.09 | 11500 | 0.4528 | 0.3572 |
77
+ | 0.2269 | 15.75 | 12000 | 0.4613 | 0.3590 |
78
+ | 0.2109 | 16.4 | 12500 | 0.4492 | 0.3610 |
79
+ | 0.2097 | 17.06 | 13000 | 0.4468 | 0.3522 |
80
+ | 0.1992 | 17.72 | 13500 | 0.4520 | 0.3531 |
81
+ | 0.1949 | 18.37 | 14000 | 0.4782 | 0.3525 |
82
+ | 0.1924 | 19.03 | 14500 | 0.4643 | 0.3459 |
83
+ | 0.1906 | 19.69 | 15000 | 0.4839 | 0.3519 |
84
+ | 0.1837 | 20.34 | 15500 | 0.4891 | 0.3427 |
85
+ | 0.1744 | 21.0 | 16000 | 0.4905 | 0.3481 |
86
+ | 0.1705 | 21.65 | 16500 | 0.4758 | 0.3445 |
87
+ | 0.1697 | 22.31 | 17000 | 0.4765 | 0.3441 |
88
+ | 0.1657 | 22.97 | 17500 | 0.5059 | 0.3447 |
89
+ | 0.1582 | 23.62 | 18000 | 0.4941 | 0.3446 |
90
+ | 0.159 | 24.28 | 18500 | 0.4977 | 0.3469 |
91
+ | 0.1562 | 24.93 | 19000 | 0.4966 | 0.3415 |
92
+ | 0.1516 | 25.59 | 19500 | 0.5130 | 0.3403 |
93
+ | 0.144 | 26.25 | 20000 | 0.5049 | 0.3390 |
94
+ | 0.1429 | 26.9 | 20500 | 0.5130 | 0.3355 |
95
+ | 0.1378 | 27.56 | 21000 | 0.5140 | 0.3371 |
96
+ | 0.1436 | 28.22 | 21500 | 0.5172 | 0.3351 |
97
+ | 0.1363 | 28.87 | 22000 | 0.5215 | 0.3361 |
98
+ | 0.1332 | 29.53 | 22500 | 0.5156 | 0.3337 |
99
 
100
 
101
  ### Framework versions
config.json CHANGED
@@ -77,7 +77,7 @@
77
  "num_hidden_layers": 24,
78
  "num_negatives": 100,
79
  "output_hidden_size": 1024,
80
- "pad_token_id": 91,
81
  "proj_codevector_dim": 768,
82
  "tdnn_dilation": [
83
  1,
@@ -103,6 +103,6 @@
103
  "torch_dtype": "float32",
104
  "transformers_version": "4.39.3",
105
  "use_weighted_layer_sum": false,
106
- "vocab_size": 94,
107
  "xvector_output_dim": 512
108
  }
 
77
  "num_hidden_layers": 24,
78
  "num_negatives": 100,
79
  "output_hidden_size": 1024,
80
+ "pad_token_id": 109,
81
  "proj_codevector_dim": 768,
82
  "tdnn_dilation": [
83
  1,
 
103
  "torch_dtype": "float32",
104
  "transformers_version": "4.39.3",
105
  "use_weighted_layer_sum": false,
106
+ "vocab_size": 112,
107
  "xvector_output_dim": 512
108
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5efe6ce6092356f8c1ccee3beafa85db0f06d0ec1164330fa05cd28b8037e2ee
3
- size 1262192880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa2521c900de82290ac51d4fbfd019d9fc9cbd9f8c2e5ba95f901335f144f77
3
+ size 1262266680
runs/May13_16-27-39_4434df775738/events.out.tfevents.1715617851.4434df775738.23.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14f46bdfd8b503cbb4748336d78ffcd4821e44d8b3ad0f4d24ca6277e68bd8e
3
+ size 30336
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:144280b8e5d570391ec69f8ba06c0c4ea2888de77b33eb2810614b90ceabe5a8
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15b880d8a777b321f75a59940f7bb20d4609b3e1b84212c285402a058a5457cc
3
  size 4920