Hugging Face's logo

Lakoc
/
ED_small_cv_en_continue2

Transformers
Safetensors
joint_aed_ctc_speech-encoder-decoder
Generated from Trainer
Inference Endpoints
Model card Files Community
Lakoc commited on
Commit
e5d3c2a
•
1 Parent(s): 303bcaf

End of training

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. README.md +42 -2
  3. generation_config.json +1 -0
  4. model.safetensors +1 -1
  5. predictions_common_voice_13_en_common_voice_13_en_test_wer21.59.csv +0 -0
  6. predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn +0 -0
  7. predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn.dtl +0 -0
  8. predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn.snt.utt +3 -0
  9. predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn.sys +18 -0
  10. predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_ref.trn +0 -0
  11. training_args.bin +1 -1
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn.snt.utt filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -3,6 +3,8 @@ tags:
3
  - generated_from_trainer
4
  datasets:
5
  - common_voice_13_0
 
 
6
  model-index:
7
  - name: ED_small_cv_en_continue2
8
  results: []
@@ -14,6 +16,17 @@ should probably proofread and complete it, then remove this comment. -->
14
  # ED_small_cv_en_continue2
15
 
16
  This model is a fine-tuned version of [](https://huggingface.co/) on the common_voice_13_0 dataset.
 
 
 
 
 
 
 
 
 
 
 
17
 
18
  ## Model description
19
 
@@ -34,16 +47,43 @@ More information needed
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0005
36
  - train_batch_size: 256
37
- - eval_batch_size: 64
38
  - seed: 42
39
  - distributed_type: multi-GPU
40
  - num_devices: 2
41
  - total_train_batch_size: 512
42
- - total_eval_batch_size: 128
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - num_epochs: 50.0
46
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  ### Framework versions
48
 
49
  - Transformers 4.40.0.dev0
 
3
  - generated_from_trainer
4
  datasets:
5
  - common_voice_13_0
6
+ metrics:
7
+ - wer
8
  model-index:
9
  - name: ED_small_cv_en_continue2
10
  results: []
 
16
  # ED_small_cv_en_continue2
17
 
18
  This model is a fine-tuned version of [](https://huggingface.co/) on the common_voice_13_0 dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.1534
21
+ - Cer: 0.0838
22
+ - Wer: 0.1978
23
+ - Mer: 0.1928
24
+ - Wil: 0.3161
25
+ - Wip: 0.6839
26
+ - Hits: 122778
27
+ - Substitutions: 22066
28
+ - Deletions: 3337
29
+ - Insertions: 3914
30
 
31
  ## Model description
32
 
 
47
  The following hyperparameters were used during training:
48
  - learning_rate: 0.0005
49
  - train_batch_size: 256
50
+ - eval_batch_size: 7
51
  - seed: 42
52
  - distributed_type: multi-GPU
53
  - num_devices: 2
54
  - total_train_batch_size: 512
55
+ - total_eval_batch_size: 14
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
  - num_epochs: 50.0
59
 
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Cer | Deletions | Hits | Insertions | Validation Loss | Mer | Substitutions | Wer | Wil | Wip |
63
+ |:-------------:|:-----:|:-----:|:------:|:---------:|:------:|:----------:|:---------------:|:------:|:-------------:|:------:|:------:|:------:|
64
+ | 1.3588 | 5.0 | 7445 | 0.1570 | 5345 | 104522 | 7446 | 1.5216 | 0.3284 | 38314 | 0.3449 | 0.5094 | 0.4906 |
65
+ | 1.285 | 6.0 | 8934 | 0.1497 | 6362 | 105386 | 5691 | 1.4842 | 0.3151 | 36433 | 0.3272 | 0.4919 | 0.5081 |
66
+ | 1.7562 | 7.0 | 10423 | 0.1487 | 6144 | 106299 | 5993 | 1.4710 | 0.3105 | 35738 | 0.3231 | 0.4849 | 0.5151 |
67
+ | 1.5766 | 8.0 | 11912 | 0.1343 | 5075 | 110239 | 5997 | 1.3866 | 0.2850 | 32867 | 0.2965 | 0.4500 | 0.5500 |
68
+ | 1.478 | 9.0 | 13401 | 0.1193 | 4513 | 113519 | 5389 | 1.3274 | 0.2608 | 30149 | 0.2703 | 0.4166 | 0.5834 |
69
+ | 1.4494 | 10.0 | 14890 | 0.1141 | 4925 | 114772 | 4845 | 1.2920 | 0.2500 | 28484 | 0.2582 | 0.3998 | 0.6002 |
70
+ | 1.4086 | 11.0 | 16379 | 0.1063 | 4113 | 116948 | 4863 | 1.2627 | 0.2359 | 27120 | 0.2436 | 0.3803 | 0.6197 |
71
+ | 1.375 | 12.0 | 17868 | 0.1017 | 3817 | 118153 | 4921 | 1.2363 | 0.2283 | 26211 | 0.2359 | 0.3689 | 0.6311 |
72
+ | 1.3304 | 13.0 | 19357 | 0.0977 | 3489 | 119548 | 4862 | 1.2181 | 0.2189 | 25144 | 0.2260 | 0.3551 | 0.6449 |
73
+ | 1.3215 | 14.0 | 20846 | 0.0928 | 3994 | 120102 | 3969 | 1.1973 | 0.2106 | 24085 | 0.2163 | 0.3430 | 0.6570 |
74
+ | 1.2824 | 15.0 | 22335 | 0.0894 | 3388 | 121469 | 4429 | 1.1777 | 0.2041 | 23324 | 0.2102 | 0.3327 | 0.6673 |
75
+ | 1.2535 | 16.0 | 23824 | 0.0857 | 3131 | 122436 | 4283 | 1.1625 | 0.1970 | 22614 | 0.2026 | 0.3226 | 0.6774 |
76
+ | 1.2096 | 17.0 | 25313 | 0.0817 | 3242 | 123261 | 3842 | 1.1429 | 0.1892 | 21678 | 0.1941 | 0.3109 | 0.6891 |
77
+ | 1.1749 | 18.0 | 26802 | 0.0795 | 3384 | 123650 | 3604 | 1.1330 | 0.1854 | 21147 | 0.1899 | 0.3047 | 0.6953 |
78
+ | 1.1528 | 19.0 | 28291 | 0.0770 | 3262 | 124432 | 3579 | 1.1220 | 0.1801 | 20487 | 0.1844 | 0.2964 | 0.7036 |
79
+ | 1.1373 | 20.0 | 29780 | 0.0762 | 3197 | 124623 | 3517 | 1.1168 | 0.1785 | 20361 | 0.1827 | 0.2942 | 0.7058 |
80
+ | 1.2751 | 21.0 | 31269 | 1.1934 | 0.0921 | 0.2159 | 0.2093 | 0.3408 | 0.6592 | 120871 | 24019 | 3291 | 4681 |
81
+ | 1.2585 | 22.0 | 32758 | 1.1727 | 0.0884 | 0.2087 | 0.2022 | 0.3297 | 0.6703 | 122013 | 23124 | 3044 | 4751 |
82
+ | 1.2612 | 23.0 | 34247 | 1.1634 | 0.0863 | 0.2043 | 0.1986 | 0.3247 | 0.6753 | 122169 | 22727 | 3285 | 4260 |
83
+ | 1.2389 | 24.0 | 35736 | 1.1574 | 0.0851 | 0.2020 | 0.1964 | 0.3215 | 0.6785 | 122473 | 22496 | 3212 | 4220 |
84
+ | 1.2422 | 25.0 | 37225 | 1.1534 | 0.0838 | 0.1978 | 0.1928 | 0.3161 | 0.6839 | 122778 | 22066 | 3337 | 3914 |
85
+
86
+
87
  ### Framework versions
88
 
89
  - Transformers 4.40.0.dev0
generation_config.json CHANGED
@@ -9,6 +9,7 @@
9
  "lm_model": null,
10
  "lm_weight": 0.0,
11
  "max_length": 512,
 
12
  "pad_token_id": 3,
13
  "space_token_id": -1,
14
  "transformers_version": "4.40.0.dev0"
 
9
  "lm_model": null,
10
  "lm_weight": 0.0,
11
  "max_length": 512,
12
+ "num_beams": 10,
13
  "pad_token_id": 3,
14
  "space_token_id": -1,
15
  "transformers_version": "4.40.0.dev0"
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7ad2d85848146f6600290cb3d0e5de191445903a4cd7506d377c82a4b1fccdc
3
  size 143219080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39d5ecc29352682111068cf7b04090df266d32cfaca0db9eaeae16080a4cd86
3
  size 143219080
predictions_common_voice_13_en_common_voice_13_en_test_wer21.59.csv ADDED
The diff for this file is too large to render. See raw diff
 
predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn ADDED
The diff for this file is too large to render. See raw diff
 
predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn.dtl ADDED
The diff for this file is too large to render. See raw diff
 
predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn.snt.utt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e38180277bf0fa7755767dc4e8e49b1e18825e34e9f45284d45d60890ea619a0
3
+ size 11442191
predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn.sys ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+
3
+
4
+ SYSTEM SUMMARY PERCENTAGES by SPEAKER
5
+
6
+ ,----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------.
7
+ |/scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/ED_small_cv_en_continue2/predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_hyp.trn|
8
+ |----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
9
+ | SPKR | # Snt # Wrd | Corr Sub Del Ins Err S.Err |
10
+ |--------------------+------------------------------------------+------------------------------------------------------------------------------------------------------------------|
11
+ | utt | 16366 144036 | 81.6 15.9 2.5 3.2 21.6 67.6 |
12
+ |==================================================================================================================================================================================|
13
+ | Sum/Avg | 16366 144036 | 81.6 15.9 2.5 3.2 21.6 67.6 |
14
+ |==================================================================================================================================================================================|
15
+ | Mean | 16366.0 144036.0 | 81.6 15.9 2.5 3.2 21.6 67.6 |
16
+ | S.D. | 0.0 0.0 | 0.0 0.0 0.0 0.0 0.0 0.0 |
17
+ | Median | 16366.0 144036.0 | 81.6 15.9 2.5 3.2 21.6 67.6 |
18
+ `----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------'
predictions_common_voice_13_en_common_voice_13_en_test_wer21.59_ref.trn ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db5562fb05c74b4caf880edd897b20d37a53978dcaf90e391a126ce3933b593d
3
  size 5816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0e5f416482ecd7e88b05953698c4a8eaccdf1ce1d1c9fbdfe56328063624a3
3
  size 5816