Commit
•
62dba14
1
Parent(s):
56ac365
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: voxpopuli-wav2vec2-large-cv8-da
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# voxpopuli-wav2vec2-large-cv8-da
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-sv-voxpopuli](https://huggingface.co/facebook/wav2vec2-large-sv-voxpopuli) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 415.8608
|
| 20 |
+
- Wer: 0.4709
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 4e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 4242
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- num_epochs: 500
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 726.4764 | 5.55 | 300 | 1339.8062 | 1.0 |
|
| 56 |
+
| 574.6736 | 11.11 | 600 | 1265.3354 | 1.0 |
|
| 57 |
+
| 534.5717 | 16.66 | 900 | 1108.4810 | 1.0 |
|
| 58 |
+
| 343.2175 | 22.22 | 1200 | 669.4202 | 0.9374 |
|
| 59 |
+
| 266.4228 | 27.77 | 1500 | 522.6546 | 0.8454 |
|
| 60 |
+
| 220.443 | 33.33 | 1800 | 454.1028 | 0.7661 |
|
| 61 |
+
| 185.4214 | 38.88 | 2100 | 413.6853 | 0.7089 |
|
| 62 |
+
| 162.6397 | 44.44 | 2400 | 388.8118 | 0.6620 |
|
| 63 |
+
| 142.0146 | 49.99 | 2700 | 368.1696 | 0.6286 |
|
| 64 |
+
| 132.324 | 55.55 | 3000 | 368.3901 | 0.6071 |
|
| 65 |
+
| 117.4966 | 61.11 | 3300 | 356.1192 | 0.5831 |
|
| 66 |
+
| 106.5261 | 66.66 | 3600 | 349.3229 | 0.5655 |
|
| 67 |
+
| 95.7354 | 72.22 | 3900 | 353.2257 | 0.5534 |
|
| 68 |
+
| 91.4711 | 77.77 | 4200 | 351.9698 | 0.5453 |
|
| 69 |
+
| 86.1983 | 83.33 | 4500 | 354.0186 | 0.5454 |
|
| 70 |
+
| 77.3262 | 88.88 | 4800 | 355.5745 | 0.5390 |
|
| 71 |
+
| 73.6696 | 94.44 | 5100 | 352.2862 | 0.5282 |
|
| 72 |
+
| 69.1898 | 99.99 | 5400 | 351.4298 | 0.5223 |
|
| 73 |
+
| 66.8595 | 105.55 | 5700 | 361.5981 | 0.5151 |
|
| 74 |
+
| 61.6978 | 111.11 | 6000 | 362.9925 | 0.5097 |
|
| 75 |
+
| 58.1949 | 116.66 | 6300 | 366.9365 | 0.5060 |
|
| 76 |
+
| 54.6844 | 122.22 | 6600 | 361.5234 | 0.5074 |
|
| 77 |
+
| 54.6381 | 127.77 | 6900 | 366.7358 | 0.5045 |
|
| 78 |
+
| 52.0427 | 133.33 | 7200 | 373.6508 | 0.4990 |
|
| 79 |
+
| 48.9871 | 138.88 | 7500 | 367.0853 | 0.4964 |
|
| 80 |
+
| 46.3138 | 144.44 | 7800 | 375.1443 | 0.4979 |
|
| 81 |
+
| 44.4403 | 149.99 | 8100 | 379.8337 | 0.4925 |
|
| 82 |
+
| 45.3876 | 155.55 | 8400 | 382.2239 | 0.4862 |
|
| 83 |
+
| 42.0502 | 161.11 | 8700 | 384.0788 | 0.4867 |
|
| 84 |
+
| 40.0308 | 166.66 | 9000 | 383.6678 | 0.4802 |
|
| 85 |
+
| 39.1281 | 172.22 | 9300 | 386.4395 | 0.4814 |
|
| 86 |
+
| 37.5134 | 177.77 | 9600 | 390.5568 | 0.4752 |
|
| 87 |
+
| 38.0693 | 183.33 | 9900 | 389.8726 | 0.4786 |
|
| 88 |
+
| 35.0237 | 188.88 | 10200 | 391.2879 | 0.4725 |
|
| 89 |
+
| 36.2227 | 194.44 | 10500 | 383.9153 | 0.4776 |
|
| 90 |
+
| 34.0764 | 199.99 | 10800 | 406.2789 | 0.4798 |
|
| 91 |
+
| 33.658 | 205.55 | 11100 | 407.3349 | 0.4721 |
|
| 92 |
+
| 32.4348 | 211.11 | 11400 | 394.2111 | 0.4761 |
|
| 93 |
+
| 30.4748 | 216.66 | 11700 | 406.4054 | 0.4720 |
|
| 94 |
+
| 30.9136 | 222.22 | 12000 | 403.6569 | 0.4739 |
|
| 95 |
+
| 31.7569 | 227.77 | 12300 | 406.9623 | 0.4702 |
|
| 96 |
+
| 29.7905 | 233.33 | 12600 | 407.8719 | 0.4647 |
|
| 97 |
+
| 28.9987 | 238.88 | 12900 | 419.9362 | 0.4690 |
|
| 98 |
+
| 27.9413 | 244.44 | 13200 | 420.0189 | 0.4727 |
|
| 99 |
+
| 27.4724 | 249.99 | 13500 | 408.5531 | 0.4676 |
|
| 100 |
+
| 27.7707 | 255.55 | 13800 | 421.7307 | 0.4678 |
|
| 101 |
+
| 27.2706 | 261.11 | 14100 | 415.8608 | 0.4709 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- Transformers 4.16.2
|
| 107 |
+
- Pytorch 1.10.2+cu102
|
| 108 |
+
- Datasets 1.18.3
|
| 109 |
+
- Tokenizers 0.11.0
|