update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-base-timit-demo-google-colab
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# wav2vec2-base-timit-demo-google-colab
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.5035
|
| 18 |
+
- Wer: 0.3346
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 1000
|
| 44 |
+
- num_epochs: 30
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 50 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
| 51 |
+
| 1.1411 | 1.0 | 500 | 0.6675 | 0.6001 |
|
| 52 |
+
| 0.5668 | 2.01 | 1000 | 0.4699 | 0.4973 |
|
| 53 |
+
| 0.3773 | 3.01 | 1500 | 0.4475 | 0.4403 |
|
| 54 |
+
| 0.2696 | 4.02 | 2000 | 0.4162 | 0.4166 |
|
| 55 |
+
| 0.2165 | 5.02 | 2500 | 0.3809 | 0.4011 |
|
| 56 |
+
| 0.1849 | 6.02 | 3000 | 0.4120 | 0.3849 |
|
| 57 |
+
| 0.1542 | 7.03 | 3500 | 0.4436 | 0.3770 |
|
| 58 |
+
| 0.1385 | 8.03 | 4000 | 0.3977 | 0.3732 |
|
| 59 |
+
| 0.1224 | 9.04 | 4500 | 0.4530 | 0.3672 |
|
| 60 |
+
| 0.1233 | 10.04 | 5000 | 0.3949 | 0.3596 |
|
| 61 |
+
| 0.1078 | 11.04 | 5500 | 0.4616 | 0.3539 |
|
| 62 |
+
| 0.097 | 12.05 | 6000 | 0.4354 | 0.3697 |
|
| 63 |
+
| 0.0821 | 13.05 | 6500 | 0.4370 | 0.3643 |
|
| 64 |
+
| 0.0724 | 14.06 | 7000 | 0.4729 | 0.3587 |
|
| 65 |
+
| 0.0678 | 15.06 | 7500 | 0.5822 | 0.3742 |
|
| 66 |
+
| 0.0632 | 16.06 | 8000 | 0.4460 | 0.3513 |
|
| 67 |
+
| 0.0627 | 17.07 | 8500 | 0.5531 | 0.3537 |
|
| 68 |
+
| 0.0574 | 18.07 | 9000 | 0.5262 | 0.3575 |
|
| 69 |
+
| 0.0515 | 19.08 | 9500 | 0.4794 | 0.3488 |
|
| 70 |
+
| 0.0475 | 20.08 | 10000 | 0.4941 | 0.3458 |
|
| 71 |
+
| 0.0463 | 21.08 | 10500 | 0.4741 | 0.3377 |
|
| 72 |
+
| 0.0392 | 22.09 | 11000 | 0.5390 | 0.3381 |
|
| 73 |
+
| 0.0401 | 23.09 | 11500 | 0.4984 | 0.3413 |
|
| 74 |
+
| 0.0371 | 24.1 | 12000 | 0.5112 | 0.3460 |
|
| 75 |
+
| 0.0305 | 25.1 | 12500 | 0.5255 | 0.3418 |
|
| 76 |
+
| 0.0278 | 26.1 | 13000 | 0.5045 | 0.3389 |
|
| 77 |
+
| 0.0265 | 27.11 | 13500 | 0.4990 | 0.3371 |
|
| 78 |
+
| 0.0248 | 28.11 | 14000 | 0.5242 | 0.3362 |
|
| 79 |
+
| 0.0249 | 29.12 | 14500 | 0.5035 | 0.3346 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.17.0
|
| 85 |
+
- Pytorch 1.11.0+cu113
|
| 86 |
+
- Datasets 1.18.3
|
| 87 |
+
- Tokenizers 0.12.1
|