End of training
Browse files- .gitattributes +1 -0
- README.md +26 -24
- model.safetensors +2 -2
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.44.csv +0 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_hyp.trn +0 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_hyp.trn.dtl +0 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_hyp.trn.snt.utt +3 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_hyp.trn.sys +18 -0
- predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_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_wer19.46_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_wer19.46_hyp.trn.snt.utt filter=lfs diff=lfs merge=lfs -text
|
37 |
+
predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_hyp.trn.snt.utt filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
-
base_model: Lakoc/DeCRED_small_cv_2
|
5 |
datasets:
|
6 |
- common_voice_13_0
|
7 |
metrics:
|
@@ -18,16 +18,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [Lakoc/DeCRED_small_cv_2](https://huggingface.co/Lakoc/DeCRED_small_cv_2) on the common_voice_13_0 dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.
|
22 |
- Cer: 0.0632
|
23 |
-
- Wer: 0.
|
24 |
-
- Mer: 0.
|
25 |
- Wil: 0.2408
|
26 |
- Wip: 0.7592
|
27 |
-
- Hits:
|
28 |
-
- Substitutions:
|
29 |
-
- Deletions:
|
30 |
-
- Insertions:
|
31 |
|
32 |
## Model description
|
33 |
|
@@ -46,7 +46,7 @@ More information needed
|
|
46 |
### Training hyperparameters
|
47 |
|
48 |
The following hyperparameters were used during training:
|
49 |
-
- learning_rate: 0.
|
50 |
- train_batch_size: 256
|
51 |
- eval_batch_size: 64
|
52 |
- seed: 42
|
@@ -61,18 +61,23 @@ The following hyperparameters were used during training:
|
|
61 |
|
62 |
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Mer | Wil | Wip | Hits | Substitutions | Deletions | Insertions |
|
63 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|:------:|:-----:|:-------------:|:---------:|:----------:|
|
64 |
-
|
|
65 |
-
| 1.
|
66 |
-
| 1.
|
67 |
-
| 1.
|
68 |
-
| 1.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 1.
|
73 |
-
| 1.
|
74 |
-
| 1.
|
75 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
76 |
|
77 |
|
78 |
### Framework versions
|
@@ -81,6 +86,3 @@ The following hyperparameters were used during training:
|
|
81 |
- Pytorch 2.2.0+rocm5.6
|
82 |
- Datasets 2.18.0
|
83 |
- Tokenizers 0.15.2
|
84 |
-
|
85 |
-
### Wandb run
|
86 |
-
https://wandb.ai/butspeechfit/decred_commonvoice_en/runs/DeCRED_linear_mixing_tuning
|
|
|
1 |
---
|
2 |
+
base_model: Lakoc/DeCRED_small_cv_2
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
5 |
datasets:
|
6 |
- common_voice_13_0
|
7 |
metrics:
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [Lakoc/DeCRED_small_cv_2](https://huggingface.co/Lakoc/DeCRED_small_cv_2) on the common_voice_13_0 dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.0601
|
22 |
- Cer: 0.0632
|
23 |
+
- Wer: 0.1472
|
24 |
+
- Mer: 0.1445
|
25 |
- Wil: 0.2408
|
26 |
- Wip: 0.7592
|
27 |
+
- Hits: 23157
|
28 |
+
- Substitutions: 2930
|
29 |
+
- Deletions: 486
|
30 |
+
- Insertions: 495
|
31 |
|
32 |
## Model description
|
33 |
|
|
|
46 |
### Training hyperparameters
|
47 |
|
48 |
The following hyperparameters were used during training:
|
49 |
+
- learning_rate: 0.01
|
50 |
- train_batch_size: 256
|
51 |
- eval_batch_size: 64
|
52 |
- seed: 42
|
|
|
61 |
|
62 |
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Mer | Wil | Wip | Hits | Substitutions | Deletions | Insertions |
|
63 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:------:|:------:|:-----:|:-------------:|:---------:|:----------:|
|
64 |
+
| 3.4981 | 2.67 | 20 | 3.3391 | 3.8755 | 3.5546 | 0.9635 | 0.9950 | 0.0050 | 3582 | 22099 | 892 | 71466 |
|
65 |
+
| 1.2736 | 5.33 | 40 | 1.2175 | 0.0756 | 0.1717 | 0.1678 | 0.2775 | 0.7225 | 22623 | 3423 | 527 | 612 |
|
66 |
+
| 1.1073 | 8.0 | 60 | 1.0687 | 0.0647 | 0.1511 | 0.1483 | 0.2464 | 0.7536 | 23059 | 2993 | 521 | 501 |
|
67 |
+
| 1.0963 | 10.67 | 80 | 1.0656 | 0.0638 | 0.1492 | 0.1464 | 0.2436 | 0.7564 | 23122 | 2963 | 488 | 514 |
|
68 |
+
| 1.0811 | 13.33 | 100 | 1.0630 | 0.0636 | 0.1478 | 0.1451 | 0.2416 | 0.7584 | 23152 | 2937 | 484 | 507 |
|
69 |
+
| 1.1036 | 16.0 | 120 | 1.0617 | 0.0634 | 0.1476 | 0.1448 | 0.2410 | 0.7590 | 23160 | 2925 | 488 | 509 |
|
70 |
+
| 1.0831 | 18.67 | 140 | 1.0610 | 0.0632 | 0.1474 | 0.1447 | 0.2410 | 0.7590 | 23157 | 2931 | 485 | 501 |
|
71 |
+
| 1.0914 | 21.33 | 160 | 1.0607 | 0.0634 | 0.1478 | 0.1451 | 0.2418 | 0.7582 | 23142 | 2941 | 490 | 497 |
|
72 |
+
| 1.1033 | 24.0 | 180 | 1.0605 | 0.0631 | 0.1470 | 0.1443 | 0.2405 | 0.7595 | 23162 | 2925 | 486 | 496 |
|
73 |
+
| 1.0849 | 26.67 | 200 | 1.0603 | 0.0632 | 0.1472 | 0.1445 | 0.2407 | 0.7593 | 23159 | 2926 | 488 | 498 |
|
74 |
+
| 1.0937 | 29.33 | 220 | 1.0603 | 0.0632 | 0.1473 | 0.1445 | 0.2407 | 0.7593 | 23160 | 2925 | 488 | 500 |
|
75 |
+
| 1.1295 | 32.0 | 240 | 1.0601 | 0.0632 | 0.1471 | 0.1444 | 0.2406 | 0.7594 | 23162 | 2926 | 485 | 499 |
|
76 |
+
| 1.0741 | 34.67 | 260 | 1.0602 | 0.0631 | 0.1471 | 0.1444 | 0.2405 | 0.7595 | 23161 | 2924 | 488 | 496 |
|
77 |
+
| 1.073 | 37.33 | 280 | 1.0601 | 0.0631 | 0.1471 | 0.1444 | 0.2407 | 0.7593 | 23159 | 2927 | 487 | 496 |
|
78 |
+
| 1.0846 | 40.0 | 300 | 1.0601 | 0.0631 | 0.1471 | 0.1445 | 0.2408 | 0.7592 | 23158 | 2929 | 486 | 495 |
|
79 |
+
| 1.0717 | 42.67 | 320 | 1.0601 | 0.0632 | 0.1472 | 0.1445 | 0.2408 | 0.7592 | 23158 | 2929 | 486 | 497 |
|
80 |
+
| 1.1017 | 45.33 | 340 | 1.0601 | 0.0632 | 0.1472 | 0.1445 | 0.2408 | 0.7592 | 23157 | 2930 | 486 | 495 |
|
81 |
|
82 |
|
83 |
### Framework versions
|
|
|
86 |
- Pytorch 2.2.0+rocm5.6
|
87 |
- Datasets 2.18.0
|
88 |
- 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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a99a5ad59f0cc2e78884c6570aadddf02ec9114cf852352d0e079d69a3aac04c
|
3 |
+
size 144251296
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.44.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_wer19.44_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_wer19.44_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_wer19.44_hyp.trn.snt.utt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:507d3811282389cafe62d8998e5071e19271afc8194cae8425115704eaa3eb1f
|
3 |
+
size 11430312
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_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/DeCRED_linear_mixing_tuning/predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_hyp.trn|
|
8 |
+
|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
9 |
+
| SPKR | # Snt # Wrd | Corr Sub Del Ins Err S.Err |
|
10 |
+
|--------------------+-------------------------------------------+--------------------------------------------------------------------------------------------------------------------|
|
11 |
+
| utt | 16365 144023 | 83.3 14.2 2.5 2.7 19.4 63.1 |
|
12 |
+
|=====================================================================================================================================================================================|
|
13 |
+
| Sum/Avg | 16365 144023 | 83.3 14.2 2.5 2.7 19.4 63.1 |
|
14 |
+
|=====================================================================================================================================================================================|
|
15 |
+
| Mean | 16365.0 144023.0 | 83.3 14.2 2.5 2.7 19.4 63.1 |
|
16 |
+
| S.D. | 0.0 0.0 | 0.0 0.0 0.0 0.0 0.0 0.0 |
|
17 |
+
| Median | 16365.0 144023.0 | 83.3 14.2 2.5 2.7 19.4 63.1 |
|
18 |
+
`-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------'
|
predictions_common_voice_13_en_common_voice_13_en_test_wer19.44_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 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:315c4a2be87925de586b362d37c1c982b3c51d788cdfddab1839b822d84cfbac
|
3 |
size 5688
|