Commit
•
e0cc599
1
Parent(s):
19492d6
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-hi-wx1
|
| 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 |
+
# wav2vec2-large-xls-r-300m-hi-wx1
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6966
|
| 20 |
+
- Wer: 0.3424
|
| 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: 0.00024
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 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: 1500
|
| 48 |
+
- num_epochs: 50
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 11.0193 | 1.36 | 200 | 5.6992 | 1.0 |
|
| 56 |
+
| 3.9285 | 2.72 | 400 | 3.4430 | 1.0 |
|
| 57 |
+
| 3.293 | 4.08 | 600 | 2.7707 | 1.0 |
|
| 58 |
+
| 1.2714 | 5.44 | 800 | 0.8479 | 0.6015 |
|
| 59 |
+
| 0.6469 | 6.8 | 1000 | 0.7087 | 0.5412 |
|
| 60 |
+
| 0.4982 | 8.16 | 1200 | 0.6655 | 0.5116 |
|
| 61 |
+
| 0.4131 | 9.52 | 1400 | 0.6422 | 0.4845 |
|
| 62 |
+
| 0.3653 | 10.88 | 1600 | 0.6452 | 0.4700 |
|
| 63 |
+
| 0.3177 | 12.24 | 1800 | 0.7519 | 0.5236 |
|
| 64 |
+
| 0.2771 | 13.6 | 2000 | 0.6238 | 0.4444 |
|
| 65 |
+
| 0.2424 | 14.96 | 2200 | 0.6317 | 0.4458 |
|
| 66 |
+
| 0.2207 | 16.33 | 2400 | 0.6634 | 0.4144 |
|
| 67 |
+
| 0.1997 | 17.68 | 2600 | 0.6469 | 0.4110 |
|
| 68 |
+
| 0.1843 | 19.05 | 2800 | 0.6958 | 0.4162 |
|
| 69 |
+
| 0.1705 | 20.41 | 3000 | 0.6658 | 0.3992 |
|
| 70 |
+
| 0.1535 | 21.77 | 3200 | 0.6829 | 0.4136 |
|
| 71 |
+
| 0.1492 | 23.13 | 3400 | 0.6628 | 0.4018 |
|
| 72 |
+
| 0.1383 | 24.49 | 3600 | 0.6603 | 0.4020 |
|
| 73 |
+
| 0.1334 | 25.85 | 3800 | 0.7079 | 0.3914 |
|
| 74 |
+
| 0.1215 | 27.21 | 4000 | 0.7016 | 0.3904 |
|
| 75 |
+
| 0.1211 | 28.57 | 4200 | 0.7232 | 0.3963 |
|
| 76 |
+
| 0.1125 | 29.93 | 4400 | 0.7258 | 0.3879 |
|
| 77 |
+
| 0.1074 | 31.29 | 4600 | 0.7476 | 0.3900 |
|
| 78 |
+
| 0.0965 | 32.65 | 4800 | 0.7120 | 0.3734 |
|
| 79 |
+
| 0.0916 | 34.01 | 5000 | 0.6694 | 0.3730 |
|
| 80 |
+
| 0.0865 | 35.37 | 5200 | 0.7181 | 0.3680 |
|
| 81 |
+
| 0.0822 | 36.73 | 5400 | 0.6698 | 0.3554 |
|
| 82 |
+
| 0.0757 | 38.09 | 5600 | 0.7035 | 0.3627 |
|
| 83 |
+
| 0.0723 | 39.45 | 5800 | 0.6832 | 0.3575 |
|
| 84 |
+
| 0.0746 | 40.81 | 6000 | 0.6942 | 0.3508 |
|
| 85 |
+
| 0.0667 | 42.18 | 6200 | 0.7075 | 0.3523 |
|
| 86 |
+
| 0.0638 | 43.54 | 6400 | 0.7009 | 0.3473 |
|
| 87 |
+
| 0.0585 | 44.89 | 6600 | 0.6887 | 0.3443 |
|
| 88 |
+
| 0.0562 | 46.26 | 6800 | 0.6888 | 0.3454 |
|
| 89 |
+
| 0.0534 | 47.62 | 7000 | 0.7048 | 0.3438 |
|
| 90 |
+
| 0.0481 | 48.98 | 7200 | 0.6966 | 0.3424 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- Transformers 4.16.2
|
| 96 |
+
- Pytorch 1.10.0+cu111
|
| 97 |
+
- Datasets 1.18.3
|
| 98 |
+
- Tokenizers 0.11.0
|