End of training
Browse files- .gitattributes +1 -0
- README.md +53 -39
- model.safetensors +1 -1
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.69.csv +0 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_hyp.trn +0 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_hyp.trn.dtl +0 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_hyp.trn.snt.utt +3 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_hyp.trn.sys +18 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_ref.trn +0 -0
- training_args.bin +1 -1
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* 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_wer22.42_hyp.trn.snt.utt 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_wer22.42_hyp.trn.snt.utt filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_hyp.trn.snt.utt filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -17,16 +17,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 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 |
-
-
|
| 21 |
-
-
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
-
-
|
| 25 |
-
-
|
| 26 |
-
-
|
| 27 |
-
-
|
| 28 |
-
-
|
| 29 |
-
-
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
|
@@ -56,35 +56,52 @@ The following hyperparameters were used during training:
|
|
| 56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
- lr_scheduler_type: linear
|
| 58 |
- lr_scheduler_warmup_steps: 15000
|
| 59 |
-
- num_epochs:
|
| 60 |
|
| 61 |
### Training results
|
| 62 |
|
| 63 |
-
| Training Loss | Epoch | Step
|
| 64 |
-
|
| 65 |
-
| 1.7038 | 5.0 | 14885
|
| 66 |
-
| 1.6051 | 6.0 | 17862
|
| 67 |
-
| 1.5396 | 7.0 | 20839
|
| 68 |
-
| 1.4436 | 8.0 | 23816
|
| 69 |
-
| 1.4287 | 9.0 | 26793
|
| 70 |
-
| 1.395 | 10.0 | 29770
|
| 71 |
-
| 1.3668 | 11.0 | 32747
|
| 72 |
-
| 1.3238 | 12.0 | 35724
|
| 73 |
-
| 1.3133 | 13.0 | 38701
|
| 74 |
-
| 1.2968 | 14.0 | 41678
|
| 75 |
-
| 1.2783 | 15.0 | 44655
|
| 76 |
-
| 1.2359 | 16.0 | 47632
|
| 77 |
-
| 1.2543 | 17.0 | 50609
|
| 78 |
-
| 1.2245 | 18.0 | 53586
|
| 79 |
-
| 1.2 | 19.0 | 56563
|
| 80 |
-
| 1.1964 | 20.0 | 59540
|
| 81 |
-
| 1.1822 | 21.0 | 62517
|
| 82 |
-
| 1.1758 | 22.0 | 65494
|
| 83 |
-
| 1.1735 | 23.0 | 68471
|
| 84 |
-
| 1.1556 | 24.0 | 71448
|
| 85 |
-
| 1.1538 | 25.0 | 74425
|
| 86 |
-
| 1.1078 | 26.0 | 77402
|
| 87 |
-
| 1.1539 | 27.0 | 80379
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
|
| 89 |
|
| 90 |
### Framework versions
|
|
@@ -93,6 +110,3 @@ The following hyperparameters were used during training:
|
|
| 93 |
- Pytorch 2.2.0+rocm5.6
|
| 94 |
- Datasets 2.18.0
|
| 95 |
- Tokenizers 0.15.2
|
| 96 |
-
|
| 97 |
-
### Wandb run
|
| 98 |
-
https://wandb.ai/butspeechfit/decred_commonvoice_en/runs/ED_small_cv_v2_continue3
|
|
|
|
| 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: 1.0688
|
| 21 |
+
- Cer: 0.0677
|
| 22 |
+
- Wer: 0.1598
|
| 23 |
+
- Mer: 0.1565
|
| 24 |
+
- Wil: 0.2593
|
| 25 |
+
- Wip: 0.7407
|
| 26 |
+
- Hits: 127573
|
| 27 |
+
- Substitutions: 17637
|
| 28 |
+
- Deletions: 2971
|
| 29 |
+
- Insertions: 3069
|
| 30 |
|
| 31 |
## Model description
|
| 32 |
|
|
|
|
| 56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
- lr_scheduler_type: linear
|
| 58 |
- lr_scheduler_warmup_steps: 15000
|
| 59 |
+
- num_epochs: 70.0
|
| 60 |
|
| 61 |
### Training results
|
| 62 |
|
| 63 |
+
| Training Loss | Epoch | Step | Cer | Deletions | Hits | Insertions | Validation Loss | Mer | Substitutions | Wer | Wil | Wip |
|
| 64 |
+
|:-------------:|:-----:|:------:|:------:|:---------:|:------:|:----------:|:---------------:|:------:|:-------------:|:------:|:------:|:------:|
|
| 65 |
+
| 1.7038 | 5.0 | 14885 | 0.1731 | 6463 | 103703 | 7394 | 1.5150 | 0.3334 | 38015 | 0.3501 | 0.5133 | 0.4867 |
|
| 66 |
+
| 1.6051 | 6.0 | 17862 | 0.1512 | 6309 | 107805 | 6257 | 1.4257 | 0.3020 | 34067 | 0.3147 | 0.4705 | 0.5295 |
|
| 67 |
+
| 1.5396 | 7.0 | 20839 | 0.1368 | 5262 | 110900 | 6029 | 1.3715 | 0.2809 | 32019 | 0.2923 | 0.4428 | 0.5572 |
|
| 68 |
+
| 1.4436 | 8.0 | 23816 | 0.1299 | 5464 | 112866 | 5686 | 1.3285 | 0.2665 | 29851 | 0.2767 | 0.4207 | 0.5793 |
|
| 69 |
+
| 1.4287 | 9.0 | 26793 | 0.1241 | 4793 | 114249 | 5680 | 1.3090 | 0.2575 | 29139 | 0.2673 | 0.4091 | 0.5909 |
|
| 70 |
+
| 1.395 | 10.0 | 29770 | 0.1200 | 4698 | 115580 | 5505 | 1.2842 | 0.2479 | 27903 | 0.2572 | 0.3949 | 0.6051 |
|
| 71 |
+
| 1.3668 | 11.0 | 32747 | 0.1111 | 4400 | 117281 | 4991 | 1.2510 | 0.2343 | 26500 | 0.2422 | 0.3761 | 0.6239 |
|
| 72 |
+
| 1.3238 | 12.0 | 35724 | 0.1064 | 4560 | 117845 | 4500 | 1.2363 | 0.2282 | 25776 | 0.2351 | 0.3673 | 0.6327 |
|
| 73 |
+
| 1.3133 | 13.0 | 38701 | 0.1028 | 4173 | 118971 | 4613 | 1.2215 | 0.2214 | 25037 | 0.2283 | 0.3573 | 0.6427 |
|
| 74 |
+
| 1.2968 | 14.0 | 41678 | 0.0995 | 3937 | 119798 | 4466 | 1.2026 | 0.2152 | 24446 | 0.2217 | 0.3487 | 0.6513 |
|
| 75 |
+
| 1.2783 | 15.0 | 44655 | 0.0974 | 4071 | 120231 | 4295 | 1.1939 | 0.2115 | 23879 | 0.2176 | 0.3427 | 0.6573 |
|
| 76 |
+
| 1.2359 | 16.0 | 47632 | 0.0961 | 3946 | 120640 | 4313 | 1.1884 | 0.2089 | 23595 | 0.2150 | 0.3388 | 0.6612 |
|
| 77 |
+
| 1.2543 | 17.0 | 50609 | 0.0939 | 3757 | 121623 | 4476 | 1.1743 | 0.2033 | 22801 | 0.2094 | 0.3296 | 0.6704 |
|
| 78 |
+
| 1.2245 | 18.0 | 53586 | 0.0919 | 3981 | 121522 | 3944 | 1.1690 | 0.2012 | 22678 | 0.2065 | 0.3273 | 0.6727 |
|
| 79 |
+
| 1.2 | 19.0 | 56563 | 0.0903 | 3819 | 122029 | 3995 | 1.1626 | 0.1981 | 22333 | 0.2034 | 0.3226 | 0.6774 |
|
| 80 |
+
| 1.1964 | 20.0 | 59540 | 0.0916 | 3822 | 122170 | 4154 | 1.1598 | 0.1980 | 22189 | 0.2036 | 0.3218 | 0.6782 |
|
| 81 |
+
| 1.1822 | 21.0 | 62517 | 0.0871 | 3630 | 122825 | 3981 | 1.1471 | 0.1928 | 21726 | 0.1980 | 0.3146 | 0.6854 |
|
| 82 |
+
| 1.1758 | 22.0 | 65494 | 0.0862 | 3556 | 123114 | 3918 | 1.1413 | 0.1906 | 21511 | 0.1956 | 0.3114 | 0.6886 |
|
| 83 |
+
| 1.1735 | 23.0 | 68471 | 0.0847 | 3431 | 123623 | 4013 | 1.1381 | 0.1877 | 21127 | 0.1928 | 0.3067 | 0.6933 |
|
| 84 |
+
| 1.1556 | 24.0 | 71448 | 0.0839 | 3668 | 123854 | 3698 | 1.1282 | 0.1845 | 20659 | 0.1891 | 0.3015 | 0.6985 |
|
| 85 |
+
| 1.1538 | 25.0 | 74425 | 0.0819 | 3475 | 124201 | 3716 | 1.1240 | 0.1823 | 20505 | 0.1869 | 0.2986 | 0.7014 |
|
| 86 |
+
| 1.1078 | 26.0 | 77402 | 0.0819 | 3410 | 124426 | 3751 | 1.1259 | 0.1810 | 20345 | 0.1856 | 0.2965 | 0.7035 |
|
| 87 |
+
| 1.1539 | 27.0 | 80379 | 0.0805 | 3333 | 124879 | 3716 | 1.1152 | 0.1779 | 19969 | 0.1823 | 0.2916 | 0.7084 |
|
| 88 |
+
| 1.1432 | 54.0 | 80406 | 1.1113 | 0.0787 | 0.1790 | 0.1747 | 0.2868 | 0.7132 | 125277 | 19604 | 3300 | 3619 |
|
| 89 |
+
| 1.1171 | 55.0 | 81895 | 1.0912 | 0.0744 | 0.1713 | 0.1676 | 0.2763 | 0.7237 | 126048 | 18870 | 3263 | 3245 |
|
| 90 |
+
| 1.1027 | 56.0 | 83384 | 1.0874 | 0.0740 | 0.1696 | 0.1659 | 0.2736 | 0.7264 | 126362 | 18663 | 3156 | 3309 |
|
| 91 |
+
| 1.0827 | 57.0 | 84873 | 1.0865 | 0.0725 | 0.1690 | 0.1654 | 0.2728 | 0.7272 | 126356 | 18599 | 3226 | 3214 |
|
| 92 |
+
| 1.0794 | 58.0 | 86362 | 1.0837 | 0.0717 | 0.1665 | 0.1629 | 0.2691 | 0.7309 | 126790 | 18361 | 3030 | 3287 |
|
| 93 |
+
| 1.0585 | 59.0 | 87851 | 1.0816 | 0.0710 | 0.1664 | 0.1629 | 0.2688 | 0.7312 | 126738 | 18285 | 3158 | 3218 |
|
| 94 |
+
| 1.0549 | 60.0 | 89340 | 1.0785 | 0.0707 | 0.1651 | 0.1616 | 0.2671 | 0.7329 | 126913 | 18198 | 3070 | 3195 |
|
| 95 |
+
| 1.0708 | 61.0 | 90829 | 1.0795 | 0.0704 | 0.1649 | 0.1614 | 0.2667 | 0.7333 | 126928 | 18157 | 3096 | 3178 |
|
| 96 |
+
| 1.0674 | 62.0 | 92318 | 1.0767 | 0.0699 | 0.1638 | 0.1605 | 0.2650 | 0.7350 | 126981 | 17994 | 3206 | 3071 |
|
| 97 |
+
| 1.0709 | 63.0 | 93807 | 1.0738 | 0.0699 | 0.1638 | 0.1605 | 0.2652 | 0.7348 | 126999 | 18030 | 3152 | 3096 |
|
| 98 |
+
| 1.0672 | 64.0 | 95296 | 1.0734 | 0.0687 | 0.1622 | 0.1588 | 0.2630 | 0.7370 | 127257 | 17925 | 2999 | 3105 |
|
| 99 |
+
| 1.0716 | 65.0 | 96785 | 1.0712 | 0.0685 | 0.1610 | 0.1577 | 0.2613 | 0.7387 | 127412 | 17804 | 2965 | 3082 |
|
| 100 |
+
| 1.0664 | 66.0 | 98274 | 1.0723 | 0.0686 | 0.1613 | 0.1581 | 0.2618 | 0.7382 | 127312 | 17817 | 3052 | 3039 |
|
| 101 |
+
| 1.0452 | 67.0 | 99763 | 1.0703 | 0.0681 | 0.1605 | 0.1572 | 0.2605 | 0.7395 | 127444 | 17742 | 2995 | 3041 |
|
| 102 |
+
| 1.0318 | 68.0 | 101252 | 1.0695 | 0.0679 | 0.1603 | 0.1571 | 0.2601 | 0.7399 | 127479 | 17693 | 3009 | 3049 |
|
| 103 |
+
| 1.0341 | 69.0 | 102741 | 1.0686 | 0.0677 | 0.1597 | 0.1565 | 0.2590 | 0.7410 | 127600 | 17599 | 2982 | 3088 |
|
| 104 |
+
| 1.0338 | 70.0 | 104230 | 1.0688 | 0.0677 | 0.1598 | 0.1565 | 0.2593 | 0.7407 | 127573 | 17637 | 2971 | 3069 |
|
| 105 |
|
| 106 |
|
| 107 |
### Framework versions
|
|
|
|
| 110 |
- Pytorch 2.2.0+rocm5.6
|
| 111 |
- Datasets 2.18.0
|
| 112 |
- Tokenizers 0.15.2
|
|
|
|
|
|
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 143219080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73cce251b5893068e4230d7315a13d3c567482662f407dfe7c16d5f7a93d10d1
|
| 3 |
size 143219080
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.69.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_wer19.69_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_wer19.69_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_wer19.69_hyp.trn.snt.utt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b90738aba0613777cd581715a99d06954ffe516bfbd7b30e39acd55b0197c44
|
| 3 |
+
size 11444711
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_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_v2/predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_hyp.trn|
|
| 8 |
+
|------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 9 |
+
| SPKR | # Snt # Wrd | Corr Sub Del Ins Err S.Err |
|
| 10 |
+
|-------------------+----------------------------------------+-----------------------------------------------------------------------------------------------------------|
|
| 11 |
+
| utt | 16384 144172 | 83.0 14.3 2.7 2.7 19.7 63.7 |
|
| 12 |
+
|========================================================================================================================================================================|
|
| 13 |
+
| Sum/Avg | 16384 144172 | 83.0 14.3 2.7 2.7 19.7 63.7 |
|
| 14 |
+
|========================================================================================================================================================================|
|
| 15 |
+
| Mean | 16384.0 144172.0 | 83.0 14.3 2.7 2.7 19.7 63.7 |
|
| 16 |
+
| S.D. | 0.0 0.0 | 0.0 0.0 0.0 0.0 0.0 0.0 |
|
| 17 |
+
| Median | 16384.0 144172.0 | 83.0 14.3 2.7 2.7 19.7 63.7 |
|
| 18 |
+
`------------------------------------------------------------------------------------------------------------------------------------------------------------------------'
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.69_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:
|
| 3 |
size 5816
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b13090ea7d998d9981889aa3b084242294953295b5c379131f4d9ec2fe35c5e
|
| 3 |
size 5816
|