Hugging Face's logo

DewiBrynJones
/
wav2vec2-xlsr-53-ft-btb-ccv-cy

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DewiBrynJones commited on
Commit
150d894
•
1 Parent(s): 25f78d1

Model save

Browse files
Files changed (3) hide show
  1. README.md +57 -109
  2. model.safetensors +1 -1
  3. runs/May29_11-47-47_5cce808c63ba/events.out.tfevents.1716980354.5cce808c63ba.1059.0 +2 -2
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
5
- - automatic-speech-recognition
6
- - DewiBrynJones/banc-trawsgrifiadau-bangor-clean-with-ccv
7
  - generated_from_trainer
8
  metrics:
9
  - wer
@@ -17,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # wav2vec2-xlsr-53-ft-btb-ccv-cy
19
 
20
- This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the DEWIBRYNJONES/BANC-TRAWSGRIFIADAU-BANGOR-CLEAN-WITH-CCV - DEFAULT dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 2.8074
23
- - Wer: 0.9983
24
 
25
  ## Model description
26
 
@@ -45,114 +43,64 @@ The following hyperparameters were used during training:
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 1000
49
- - training_steps: 10000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Wer |
55
- |:-------------:|:------:|:-----:|:---------------:|:------:|
56
- | No log | 0.0566 | 100 | 4.1582 | 1.0 |
57
- | No log | 0.1133 | 200 | 3.1276 | 1.0 |
58
- | No log | 0.1699 | 300 | 3.4072 | 1.0 |
59
- | No log | 0.2265 | 400 | 2.1967 | 0.9899 |
60
- | 4.6703 | 0.2831 | 500 | 1.0576 | 0.7174 |
61
- | 4.6703 | 0.3398 | 600 | 0.8877 | 0.6405 |
62
- | 4.6703 | 0.3964 | 700 | 0.7894 | 0.5861 |
63
- | 4.6703 | 0.4530 | 800 | 0.7699 | 0.5877 |
64
- | 4.6703 | 0.5096 | 900 | 0.7605 | 0.5403 |
65
- | 0.5242 | 0.5663 | 1000 | 0.7429 | 0.5495 |
66
- | 0.5242 | 0.6229 | 1100 | 0.6762 | 0.5081 |
67
- | 0.5242 | 0.6795 | 1200 | 0.6703 | 0.5072 |
68
- | 0.5242 | 0.7361 | 1300 | 0.6187 | 0.4623 |
69
- | 0.5242 | 0.7928 | 1400 | 0.6205 | 0.4742 |
70
- | 0.4093 | 0.8494 | 1500 | 0.6089 | 0.4607 |
71
- | 0.4093 | 0.9060 | 1600 | 0.6079 | 0.4564 |
72
- | 0.4093 | 0.9626 | 1700 | 0.5752 | 0.4487 |
73
- | 0.4093 | 1.0193 | 1800 | 0.5519 | 0.4174 |
74
- | 0.4093 | 1.0759 | 1900 | 0.5468 | 0.4107 |
75
- | 0.3366 | 1.1325 | 2000 | 0.5372 | 0.4080 |
76
- | 0.3366 | 1.1891 | 2100 | 0.5359 | 0.4072 |
77
- | 0.3366 | 1.2458 | 2200 | 0.5304 | 0.4023 |
78
- | 0.3366 | 1.3024 | 2300 | 0.5311 | 0.4011 |
79
- | 0.3366 | 1.3590 | 2400 | 0.5186 | 0.3864 |
80
- | 0.2939 | 1.4156 | 2500 | 0.5234 | 0.3934 |
81
- | 0.2939 | 1.4723 | 2600 | 0.5213 | 0.3973 |
82
- | 0.2939 | 1.5289 | 2700 | 0.5156 | 0.3877 |
83
- | 0.2939 | 1.5855 | 2800 | 0.5052 | 0.3898 |
84
- | 0.2939 | 1.6421 | 2900 | 0.4981 | 0.3833 |
85
- | 0.2838 | 1.6988 | 3000 | 0.4990 | 0.3804 |
86
- | 0.2838 | 1.7554 | 3100 | 0.5000 | 0.3807 |
87
- | 0.2838 | 1.8120 | 3200 | 0.4961 | 0.3751 |
88
- | 0.2838 | 1.8686 | 3300 | 0.4859 | 0.3731 |
89
- | 0.2838 | 1.9253 | 3400 | 0.4812 | 0.3657 |
90
- | 0.2694 | 1.9819 | 3500 | 0.4779 | 0.3620 |
91
- | 0.2694 | 2.0385 | 3600 | 0.4943 | 0.3633 |
92
- | 0.2694 | 2.0951 | 3700 | 0.4880 | 0.3677 |
93
- | 0.2694 | 2.1518 | 3800 | 0.4990 | 0.3662 |
94
- | 0.2694 | 2.2084 | 3900 | 0.5101 | 0.3699 |
95
- | 0.2419 | 2.2650 | 4000 | 0.5393 | 0.3902 |
96
- | 0.2419 | 2.3216 | 4100 | 0.6454 | 0.4513 |
97
- | 0.2419 | 2.3783 | 4200 | 0.9892 | 0.5937 |
98
- | 0.2419 | 2.4349 | 4300 | 0.7712 | 0.5167 |
99
- | 0.2419 | 2.4915 | 4400 | 0.6338 | 0.4788 |
100
- | 0.46 | 2.5481 | 4500 | 0.5562 | 0.4156 |
101
- | 0.46 | 2.6048 | 4600 | 0.5377 | 0.3906 |
102
- | 0.46 | 2.6614 | 4700 | 0.5687 | 0.4008 |
103
- | 0.46 | 2.7180 | 4800 | 0.6321 | 0.4291 |
104
- | 0.46 | 2.7746 | 4900 | 0.5834 | 0.4203 |
105
- | 0.299 | 2.8313 | 5000 | 0.5302 | 0.3930 |
106
- | 0.299 | 2.8879 | 5100 | 0.5316 | 0.3860 |
107
- | 0.299 | 2.9445 | 5200 | 0.5344 | 0.3800 |
108
- | 0.299 | 3.0011 | 5300 | 0.5349 | 0.3842 |
109
- | 0.299 | 3.0578 | 5400 | 0.5776 | 0.4183 |
110
- | 0.2839 | 3.1144 | 5500 | 0.5883 | 0.4100 |
111
- | 0.2839 | 3.1710 | 5600 | 0.5723 | 0.4044 |
112
- | 0.2839 | 3.2276 | 5700 | 0.5630 | 0.4078 |
113
- | 0.2839 | 3.2843 | 5800 | 0.5810 | 0.4191 |
114
- | 0.2839 | 3.3409 | 5900 | 0.5996 | 0.4228 |
115
- | 0.3019 | 3.3975 | 6000 | 0.5682 | 0.4016 |
116
- | 0.3019 | 3.4541 | 6100 | 0.5561 | 0.4057 |
117
- | 0.3019 | 3.5108 | 6200 | 0.5905 | 0.4146 |
118
- | 0.3019 | 3.5674 | 6300 | 0.5875 | 0.4190 |
119
- | 0.3019 | 3.6240 | 6400 | 0.5878 | 0.4446 |
120
- | 0.2944 | 3.6806 | 6500 | 0.5939 | 0.4404 |
121
- | 0.2944 | 3.7373 | 6600 | 0.5903 | 0.4183 |
122
- | 0.2944 | 3.7939 | 6700 | 0.5808 | 0.4059 |
123
- | 0.2944 | 3.8505 | 6800 | 0.6155 | 0.4101 |
124
- | 0.2944 | 3.9071 | 6900 | 0.7987 | 0.5823 |
125
- | 0.3918 | 3.9638 | 7000 | 0.9750 | 0.5545 |
126
- | 0.3918 | 4.0204 | 7100 | 1.0540 | 0.5689 |
127
- | 0.3918 | 4.0770 | 7200 | 0.6851 | 0.4396 |
128
- | 0.3918 | 4.1336 | 7300 | 0.7332 | 0.4973 |
129
- | 0.3918 | 4.1903 | 7400 | 0.9466 | 0.6395 |
130
- | 0.5378 | 4.2469 | 7500 | 0.8257 | 0.4851 |
131
- | 0.5378 | 4.3035 | 7600 | 0.8490 | 0.4867 |
132
- | 0.5378 | 4.3601 | 7700 | 0.8717 | 0.4711 |
133
- | 0.5378 | 4.4168 | 7800 | 0.8839 | 0.5860 |
134
- | 0.5378 | 4.4734 | 7900 | 2.9113 | 1.0 |
135
- | 1.3847 | 4.5300 | 8000 | 2.8576 | 1.0 |
136
- | 1.3847 | 4.5866 | 8100 | 2.8391 | 1.0 |
137
- | 1.3847 | 4.6433 | 8200 | 2.8406 | 1.0 |
138
- | 1.3847 | 4.6999 | 8300 | 2.8566 | 1.0 |
139
- | 1.3847 | 4.7565 | 8400 | 2.8454 | 0.9998 |
140
- | 2.8136 | 4.8131 | 8500 | 2.8340 | 0.9999 |
141
- | 2.8136 | 4.8698 | 8600 | 2.8367 | 0.9999 |
142
- | 2.8136 | 4.9264 | 8700 | 2.8334 | 0.9999 |
143
- | 2.8136 | 4.9830 | 8800 | 2.8321 | 0.9999 |
144
- | 2.8136 | 5.0396 | 8900 | 2.8025 | 0.9982 |
145
- | 2.8007 | 5.0963 | 9000 | 2.8024 | 0.9975 |
146
- | 2.8007 | 5.1529 | 9100 | 2.8043 | 0.9981 |
147
- | 2.8007 | 5.2095 | 9200 | 2.8106 | 0.9992 |
148
- | 2.8007 | 5.2661 | 9300 | 2.8067 | 0.9993 |
149
- | 2.8007 | 5.3228 | 9400 | 2.8053 | 0.9986 |
150
- | 2.7935 | 5.3794 | 9500 | 2.8077 | 0.9978 |
151
- | 2.7935 | 5.4360 | 9600 | 2.8083 | 0.9987 |
152
- | 2.7935 | 5.4926 | 9700 | 2.8080 | 0.9989 |
153
- | 2.7935 | 5.5493 | 9800 | 2.8086 | 0.9986 |
154
- | 2.7935 | 5.6059 | 9900 | 2.8079 | 0.9982 |
155
- | 2.7861 | 5.6625 | 10000 | 2.8074 | 0.9983 |
156
 
157
 
158
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: facebook/wav2vec2-large-xlsr-53
4
  tags:
 
 
5
  - generated_from_trainer
6
  metrics:
7
  - wer
 
15
 
16
  # wav2vec2-xlsr-53-ft-btb-ccv-cy
17
 
18
+ This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.6956
21
+ - Wer: 0.7702
22
 
23
  ## Model description
24
 
 
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: 500
47
+ - training_steps: 5000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
53
+ |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | No log | 0.1548 | 100 | 3.5587 | 1.0 |
55
+ | No log | 0.3096 | 200 | 3.2506 | 1.0 |
56
+ | No log | 0.4644 | 300 | 2.7740 | 1.0000 |
57
+ | No log | 0.6192 | 400 | 1.1196 | 0.7807 |
58
+ | 3.6484 | 0.7740 | 500 | 0.9134 | 0.6539 |
59
+ | 3.6484 | 0.9288 | 600 | 0.7675 | 0.5923 |
60
+ | 3.6484 | 1.0836 | 700 | 0.7208 | 0.5290 |
61
+ | 3.6484 | 1.2384 | 800 | 0.6209 | 0.4745 |
62
+ | 3.6484 | 1.3932 | 900 | 0.6220 | 0.4788 |
63
+ | 0.6286 | 1.5480 | 1000 | 0.5739 | 0.4588 |
64
+ | 0.6286 | 1.7028 | 1100 | 0.5642 | 0.4262 |
65
+ | 0.6286 | 1.8576 | 1200 | 0.5512 | 0.4208 |
66
+ | 0.6286 | 2.0124 | 1300 | 0.5275 | 0.3865 |
67
+ | 0.6286 | 2.1672 | 1400 | 0.4955 | 0.3755 |
68
+ | 0.4816 | 2.3220 | 1500 | 0.4909 | 0.3733 |
69
+ | 0.4816 | 2.4768 | 1600 | 0.4983 | 0.3728 |
70
+ | 0.4816 | 2.6316 | 1700 | 0.4891 | 0.3655 |
71
+ | 0.4816 | 2.7864 | 1800 | 0.4796 | 0.3571 |
72
+ | 0.4816 | 2.9412 | 1900 | 0.4643 | 0.3592 |
73
+ | 0.4017 | 3.0960 | 2000 | 0.5085 | 0.3698 |
74
+ | 0.4017 | 3.2508 | 2100 | 0.6755 | 0.4530 |
75
+ | 0.4017 | 3.4056 | 2200 | 0.7100 | 0.5108 |
76
+ | 0.4017 | 3.5604 | 2300 | 0.8311 | 0.5643 |
77
+ | 0.4017 | 3.7152 | 2400 | 0.7032 | 0.5029 |
78
+ | 0.6839 | 3.8700 | 2500 | 0.7071 | 0.5007 |
79
+ | 0.6839 | 4.0248 | 2600 | 0.8224 | 0.5069 |
80
+ | 0.6839 | 4.1796 | 2700 | 0.8344 | 0.5162 |
81
+ | 0.6839 | 4.3344 | 2800 | 0.9089 | 0.5620 |
82
+ | 0.6839 | 4.4892 | 2900 | 0.9665 | 0.5640 |
83
+ | 0.8292 | 4.6440 | 3000 | 0.9128 | 0.5415 |
84
+ | 0.8292 | 4.7988 | 3100 | 1.1925 | 0.5939 |
85
+ | 0.8292 | 4.9536 | 3200 | 1.4327 | 0.6999 |
86
+ | 0.8292 | 5.1084 | 3300 | 1.2741 | 0.7827 |
87
+ | 0.8292 | 5.2632 | 3400 | 1.9348 | 0.8742 |
88
+ | 1.4131 | 5.4180 | 3500 | 1.9216 | 0.9870 |
89
+ | 1.4131 | 5.5728 | 3600 | 1.8565 | 0.9367 |
90
+ | 1.4131 | 5.7276 | 3700 | 1.7828 | 0.8240 |
91
+ | 1.4131 | 5.8824 | 3800 | 1.6847 | 0.8059 |
92
+ | 1.4131 | 6.0372 | 3900 | 1.6440 | 0.7984 |
93
+ | 1.7728 | 6.1920 | 4000 | 1.6765 | 0.8053 |
94
+ | 1.7728 | 6.3467 | 4100 | 1.6733 | 0.8024 |
95
+ | 1.7728 | 6.5015 | 4200 | 1.6601 | 0.7900 |
96
+ | 1.7728 | 6.6563 | 4300 | 1.6605 | 0.7973 |
97
+ | 1.7728 | 6.8111 | 4400 | 1.6599 | 0.7805 |
98
+ | 1.6777 | 6.9659 | 4500 | 1.6359 | 0.7693 |
99
+ | 1.6777 | 7.1207 | 4600 | 1.6400 | 0.7651 |
100
+ | 1.6777 | 7.2755 | 4700 | 1.6759 | 0.7672 |
101
+ | 1.6777 | 7.4303 | 4800 | 1.6849 | 0.7686 |
102
+ | 1.6777 | 7.5851 | 4900 | 1.6858 | 0.7690 |
103
+ | 1.683 | 7.7399 | 5000 | 1.6956 | 0.7702 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
104
 
105
 
106
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a7af7f53d300b5d0e45815b0146e45d184fde3cea4430ed5b43259e598e1bfd
3
  size 1261996080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fbbff955e1bb97999d07a69069b371bc39989a944a6209779d3bc67e1da9ce5
3
  size 1261996080
runs/May29_11-47-47_5cce808c63ba/events.out.tfevents.1716980354.5cce808c63ba.1059.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7998f68a55fffbb69bfa904e0081e023c0f425bacbcab219c69ef4aa7b3675c9
3
- size 23594
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59962528710419de3bb47f5f60119995f8f085271f3c4e3abf909e73ab65bdd9
3
+ size 24795