Hugging Face's logo

ducha07
/
ASR-test

Automatic Speech Recognition
Transformers
Safetensors
Vietnamese
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
ducha07 commited on
Commit
7d11083
•
1 Parent(s): 2a0e2f4

End of training

Browse files
Files changed (3) hide show
  1. README.md +117 -51
  2. adapter.vie.safetensors +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -10,7 +10,7 @@ datasets:
10
  metrics:
11
  - wer
12
  model-index:
13
- - name: ASR-test
14
  results:
15
  - task:
16
  name: Automatic Speech Recognition
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 0.2882930019620667
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the HTV news dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.5663
35
- - Wer: 0.2883
36
 
37
  ## Model description
38
 
@@ -58,61 +58,127 @@ The following hyperparameters were used during training:
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
  - lr_scheduler_warmup_steps: 100
61
- - num_epochs: 40
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
- | Training Loss | Epoch | Step | Validation Loss | Wer |
67
- |:-------------:|:-----:|:----:|:---------------:|:------:|
68
- | 4.772 | 0.92 | 100 | 0.8456 | 0.4411 |
69
- | 1.1042 | 1.83 | 200 | 0.7041 | 0.4076 |
70
- | 0.9814 | 2.75 | 300 | 0.7243 | 0.3782 |
71
- | 0.9096 | 3.67 | 400 | 0.6771 | 0.3655 |
72
- | 0.8823 | 4.59 | 500 | 0.6265 | 0.3627 |
73
- | 0.8435 | 5.5 | 600 | 0.6200 | 0.3543 |
74
- | 0.8157 | 6.42 | 700 | 0.6414 | 0.3417 |
75
- | 0.822 | 7.34 | 800 | 0.5872 | 0.3431 |
76
- | 0.7852 | 8.26 | 900 | 0.6012 | 0.3387 |
77
- | 0.7533 | 9.17 | 1000 | 0.6023 | 0.3256 |
78
- | 0.7609 | 10.09 | 1100 | 0.5837 | 0.3444 |
79
- | 0.7568 | 11.01 | 1200 | 0.5791 | 0.3311 |
80
- | 0.7091 | 11.93 | 1300 | 0.6227 | 0.3206 |
81
- | 0.7098 | 12.84 | 1400 | 0.5766 | 0.3266 |
82
- | 0.7006 | 13.76 | 1500 | 0.6084 | 0.3117 |
83
- | 0.6673 | 14.68 | 1600 | 0.5857 | 0.3120 |
84
- | 0.6832 | 15.6 | 1700 | 0.5754 | 0.3338 |
85
- | 0.6646 | 16.51 | 1800 | 0.5963 | 0.3117 |
86
- | 0.6524 | 17.43 | 1900 | 0.5816 | 0.3137 |
87
- | 0.6385 | 18.35 | 2000 | 0.5691 | 0.3257 |
88
- | 0.6433 | 19.27 | 2100 | 0.5929 | 0.3105 |
89
- | 0.6129 | 20.18 | 2200 | 0.5709 | 0.3067 |
90
- | 0.624 | 21.1 | 2300 | 0.5686 | 0.3168 |
91
- | 0.6128 | 22.02 | 2400 | 0.5867 | 0.3080 |
92
- | 0.584 | 22.94 | 2500 | 0.5680 | 0.3101 |
93
- | 0.5956 | 23.85 | 2600 | 0.5611 | 0.3023 |
94
- | 0.5825 | 24.77 | 2700 | 0.5821 | 0.2999 |
95
- | 0.56 | 25.69 | 2800 | 0.5622 | 0.3012 |
96
- | 0.56 | 26.61 | 2900 | 0.5590 | 0.3053 |
97
- | 0.5523 | 27.52 | 3000 | 0.5758 | 0.2967 |
98
- | 0.5335 | 28.44 | 3100 | 0.5649 | 0.3090 |
99
- | 0.5686 | 29.36 | 3200 | 0.5703 | 0.2931 |
100
- | 0.5488 | 30.28 | 3300 | 0.5709 | 0.2921 |
101
- | 0.5249 | 31.19 | 3400 | 0.5646 | 0.2973 |
102
- | 0.5278 | 32.11 | 3500 | 0.5628 | 0.2933 |
103
- | 0.5252 | 33.03 | 3600 | 0.5663 | 0.2927 |
104
- | 0.5092 | 33.94 | 3700 | 0.5618 | 0.2922 |
105
- | 0.5099 | 34.86 | 3800 | 0.5616 | 0.2954 |
106
- | 0.5031 | 35.78 | 3900 | 0.5670 | 0.2913 |
107
- | 0.4959 | 36.7 | 4000 | 0.5679 | 0.2923 |
108
- | 0.4936 | 37.61 | 4100 | 0.5675 | 0.2912 |
109
- | 0.5012 | 38.53 | 4200 | 0.5661 | 0.2897 |
110
- | 0.4819 | 39.45 | 4300 | 0.5663 | 0.2883 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
 
112
 
113
  ### Framework versions
114
 
115
  - Transformers 4.37.0.dev0
116
  - Pytorch 2.1.0+cu121
117
- - Datasets 2.15.0
118
  - Tokenizers 0.15.0
 
10
  metrics:
11
  - wer
12
  model-index:
13
+ - name: ASR-test-1
14
  results:
15
  - task:
16
  name: Automatic Speech Recognition
 
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 0.2796665364074508
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the HTV news dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.6593
35
+ - Wer: 0.2797
36
 
37
  ## Model description
38
 
 
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
  - lr_scheduler_warmup_steps: 100
61
+ - num_epochs: 100
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
68
+ | 4.8562 | 0.92 | 100 | 0.8316 | 0.4500 |
69
+ | 1.0777 | 1.83 | 200 | 0.6898 | 0.3899 |
70
+ | 0.98 | 2.75 | 300 | 0.6811 | 0.3740 |
71
+ | 0.8967 | 3.67 | 400 | 0.6332 | 0.3565 |
72
+ | 0.8965 | 4.59 | 500 | 0.6038 | 0.3517 |
73
+ | 0.8396 | 5.5 | 600 | 0.6040 | 0.3479 |
74
+ | 0.8137 | 6.42 | 700 | 0.5929 | 0.3408 |
75
+ | 0.8304 | 7.34 | 800 | 0.5911 | 0.3513 |
76
+ | 0.7894 | 8.26 | 900 | 0.6078 | 0.3357 |
77
+ | 0.7412 | 9.17 | 1000 | 0.6214 | 0.3230 |
78
+ | 0.7653 | 10.09 | 1100 | 0.5869 | 0.3444 |
79
+ | 0.7437 | 11.01 | 1200 | 0.5906 | 0.3213 |
80
+ | 0.7083 | 11.93 | 1300 | 0.5952 | 0.3139 |
81
+ | 0.7168 | 12.84 | 1400 | 0.5721 | 0.3267 |
82
+ | 0.7008 | 13.76 | 1500 | 0.5895 | 0.3177 |
83
+ | 0.6825 | 14.68 | 1600 | 0.5909 | 0.3098 |
84
+ | 0.6989 | 15.6 | 1700 | 0.5979 | 0.3673 |
85
+ | 0.6717 | 16.51 | 1800 | 0.5863 | 0.3077 |
86
+ | 0.6496 | 17.43 | 1900 | 0.5798 | 0.3043 |
87
+ | 0.6609 | 18.35 | 2000 | 0.5787 | 0.3555 |
88
+ | 0.628 | 19.27 | 2100 | 0.5889 | 0.3133 |
89
+ | 0.6322 | 20.18 | 2200 | 0.5913 | 0.3077 |
90
+ | 0.634 | 21.1 | 2300 | 0.5769 | 0.3193 |
91
+ | 0.6172 | 22.02 | 2400 | 0.5731 | 0.3005 |
92
+ | 0.6043 | 22.94 | 2500 | 0.5820 | 0.3075 |
93
+ | 0.6051 | 23.85 | 2600 | 0.5831 | 0.3435 |
94
+ | 0.5865 | 24.77 | 2700 | 0.5790 | 0.3029 |
95
+ | 0.5806 | 25.69 | 2800 | 0.5945 | 0.3053 |
96
+ | 0.5901 | 26.61 | 2900 | 0.5780 | 0.3126 |
97
+ | 0.5769 | 27.52 | 3000 | 0.5732 | 0.2963 |
98
+ | 0.5539 | 28.44 | 3100 | 0.5837 | 0.2950 |
99
+ | 0.5799 | 29.36 | 3200 | 0.5835 | 0.3178 |
100
+ | 0.5518 | 30.28 | 3300 | 0.5941 | 0.2943 |
101
+ | 0.549 | 31.19 | 3400 | 0.5960 | 0.2979 |
102
+ | 0.5612 | 32.11 | 3500 | 0.5747 | 0.3167 |
103
+ | 0.5411 | 33.03 | 3600 | 0.5855 | 0.2978 |
104
+ | 0.536 | 33.94 | 3700 | 0.5720 | 0.2944 |
105
+ | 0.5329 | 34.86 | 3800 | 0.5998 | 0.3186 |
106
+ | 0.5185 | 35.78 | 3900 | 0.5936 | 0.2884 |
107
+ | 0.5186 | 36.7 | 4000 | 0.5773 | 0.2901 |
108
+ | 0.5027 | 37.61 | 4100 | 0.5969 | 0.3264 |
109
+ | 0.52 | 38.53 | 4200 | 0.6184 | 0.2939 |
110
+ | 0.4992 | 39.45 | 4300 | 0.5887 | 0.2943 |
111
+ | 0.5064 | 40.37 | 4400 | 0.5814 | 0.2966 |
112
+ | 0.4928 | 41.28 | 4500 | 0.6128 | 0.2902 |
113
+ | 0.508 | 42.2 | 4600 | 0.5943 | 0.2923 |
114
+ | 0.4887 | 43.12 | 4700 | 0.6100 | 0.3039 |
115
+ | 0.4872 | 44.04 | 4800 | 0.6044 | 0.2875 |
116
+ | 0.4711 | 44.95 | 4900 | 0.5961 | 0.2974 |
117
+ | 0.4813 | 45.87 | 5000 | 0.6022 | 0.2945 |
118
+ | 0.4818 | 46.79 | 5100 | 0.6199 | 0.2898 |
119
+ | 0.4492 | 47.71 | 5200 | 0.6161 | 0.2943 |
120
+ | 0.4715 | 48.62 | 5300 | 0.6038 | 0.2838 |
121
+ | 0.4601 | 49.54 | 5400 | 0.6223 | 0.2829 |
122
+ | 0.4432 | 50.46 | 5500 | 0.6058 | 0.2965 |
123
+ | 0.4419 | 51.38 | 5600 | 0.6134 | 0.2917 |
124
+ | 0.4564 | 52.29 | 5700 | 0.6124 | 0.2857 |
125
+ | 0.4349 | 53.21 | 5800 | 0.6229 | 0.2877 |
126
+ | 0.4358 | 54.13 | 5900 | 0.6095 | 0.2898 |
127
+ | 0.4432 | 55.05 | 6000 | 0.6365 | 0.2881 |
128
+ | 0.4277 | 55.96 | 6100 | 0.6169 | 0.2870 |
129
+ | 0.4397 | 56.88 | 6200 | 0.6174 | 0.2849 |
130
+ | 0.4245 | 57.8 | 6300 | 0.6340 | 0.2858 |
131
+ | 0.4203 | 58.72 | 6400 | 0.6321 | 0.2909 |
132
+ | 0.4112 | 59.63 | 6500 | 0.6243 | 0.2866 |
133
+ | 0.4244 | 60.55 | 6600 | 0.6318 | 0.2775 |
134
+ | 0.4119 | 61.47 | 6700 | 0.6215 | 0.2798 |
135
+ | 0.403 | 62.39 | 6800 | 0.6213 | 0.2829 |
136
+ | 0.4158 | 63.3 | 6900 | 0.6451 | 0.2795 |
137
+ | 0.3997 | 64.22 | 7000 | 0.6317 | 0.2854 |
138
+ | 0.4006 | 65.14 | 7100 | 0.6329 | 0.2846 |
139
+ | 0.4051 | 66.06 | 7200 | 0.6318 | 0.2834 |
140
+ | 0.3953 | 66.97 | 7300 | 0.6442 | 0.2855 |
141
+ | 0.4119 | 67.89 | 7400 | 0.6345 | 0.2893 |
142
+ | 0.3976 | 68.81 | 7500 | 0.6361 | 0.2798 |
143
+ | 0.3965 | 69.72 | 7600 | 0.6355 | 0.2853 |
144
+ | 0.3957 | 70.64 | 7700 | 0.6457 | 0.2814 |
145
+ | 0.3837 | 71.56 | 7800 | 0.6396 | 0.2855 |
146
+ | 0.3893 | 72.48 | 7900 | 0.6424 | 0.2842 |
147
+ | 0.3816 | 73.39 | 8000 | 0.6496 | 0.2778 |
148
+ | 0.3855 | 74.31 | 8100 | 0.6427 | 0.2881 |
149
+ | 0.3767 | 75.23 | 8200 | 0.6394 | 0.2858 |
150
+ | 0.3747 | 76.15 | 8300 | 0.6513 | 0.2844 |
151
+ | 0.3829 | 77.06 | 8400 | 0.6602 | 0.2775 |
152
+ | 0.3721 | 77.98 | 8500 | 0.6427 | 0.2825 |
153
+ | 0.3708 | 78.9 | 8600 | 0.6507 | 0.2847 |
154
+ | 0.3767 | 79.82 | 8700 | 0.6518 | 0.2816 |
155
+ | 0.3655 | 80.73 | 8800 | 0.6597 | 0.2802 |
156
+ | 0.3614 | 81.65 | 8900 | 0.6542 | 0.2781 |
157
+ | 0.3629 | 82.57 | 9000 | 0.6520 | 0.2782 |
158
+ | 0.3621 | 83.49 | 9100 | 0.6501 | 0.2797 |
159
+ | 0.3616 | 84.4 | 9200 | 0.6528 | 0.2777 |
160
+ | 0.3519 | 85.32 | 9300 | 0.6549 | 0.2798 |
161
+ | 0.3572 | 86.24 | 9400 | 0.6541 | 0.2789 |
162
+ | 0.3585 | 87.16 | 9500 | 0.6497 | 0.2778 |
163
+ | 0.3531 | 88.07 | 9600 | 0.6523 | 0.2781 |
164
+ | 0.3586 | 88.99 | 9700 | 0.6578 | 0.2789 |
165
+ | 0.3463 | 89.91 | 9800 | 0.6565 | 0.2816 |
166
+ | 0.3508 | 90.83 | 9900 | 0.6559 | 0.2797 |
167
+ | 0.3513 | 91.74 | 10000 | 0.6611 | 0.2794 |
168
+ | 0.3425 | 92.66 | 10100 | 0.6538 | 0.2804 |
169
+ | 0.3596 | 93.58 | 10200 | 0.6639 | 0.2808 |
170
+ | 0.3632 | 94.5 | 10300 | 0.6561 | 0.2789 |
171
+ | 0.348 | 95.41 | 10400 | 0.6556 | 0.2786 |
172
+ | 0.3514 | 96.33 | 10500 | 0.6575 | 0.2791 |
173
+ | 0.3499 | 97.25 | 10600 | 0.6573 | 0.2795 |
174
+ | 0.3353 | 98.17 | 10700 | 0.6589 | 0.2797 |
175
+ | 0.3468 | 99.08 | 10800 | 0.6589 | 0.2799 |
176
+ | 0.3571 | 100.0 | 10900 | 0.6593 | 0.2797 |
177
 
178
 
179
  ### Framework versions
180
 
181
  - Transformers 4.37.0.dev0
182
  - Pytorch 2.1.0+cu121
183
+ - Datasets 2.16.1
184
  - Tokenizers 0.15.0
adapter.vie.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:609f96d3ccb10717479271609e4af446794c133ea252876cf249028d2de84009
3
  size 9203360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f287d3a8e5bf04fa0d141f7721fc0f01bff07858d43b0857cfcc31075a4f24a
3
  size 9203360
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97b85b6bb08b69ade1221386d302307fe97728e208d55673e92fe559ab5f725a
3
  size 3859295720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd999975035aafe8b64406c46c2012570e16523cc250213d1e3890d4ba421b05
3
  size 3859295720