Commit ·
4cf3837
1
Parent(s): de73b17
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec_trained
|
| 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 |
+
# wav2vec_trained
|
| 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: 0.0337
|
| 18 |
+
- Wer: 0.1042
|
| 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 |
+
| 4.3849 | 2.21 | 500 | 2.9148 | 1.0 |
|
| 52 |
+
| 1.9118 | 4.42 | 1000 | 0.9627 | 0.5833 |
|
| 53 |
+
| 0.7596 | 6.64 | 1500 | 0.8953 | 0.3542 |
|
| 54 |
+
| 0.4602 | 8.85 | 2000 | 0.3325 | 0.2083 |
|
| 55 |
+
| 0.331 | 11.06 | 2500 | 0.3084 | 0.2083 |
|
| 56 |
+
| 0.2474 | 13.27 | 3000 | 0.0960 | 0.1667 |
|
| 57 |
+
| 0.1934 | 15.49 | 3500 | 0.1276 | 0.125 |
|
| 58 |
+
| 0.156 | 17.7 | 4000 | 0.0605 | 0.0833 |
|
| 59 |
+
| 0.1244 | 19.91 | 4500 | 0.0831 | 0.1458 |
|
| 60 |
+
| 0.1006 | 22.12 | 5000 | 0.0560 | 0.125 |
|
| 61 |
+
| 0.0827 | 24.34 | 5500 | 0.0395 | 0.0833 |
|
| 62 |
+
| 0.0723 | 26.55 | 6000 | 0.0573 | 0.0833 |
|
| 63 |
+
| 0.0606 | 28.76 | 6500 | 0.0337 | 0.1042 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.17.0
|
| 69 |
+
- Pytorch 1.11.0+cu113
|
| 70 |
+
- Datasets 1.18.3
|
| 71 |
+
- Tokenizers 0.12.1
|