update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-base_toy_train_data_augmented
|
| 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_toy_train_data_augmented
|
| 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: 1.0238
|
| 18 |
+
- Wer: 0.6969
|
| 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 |
+
- gradient_accumulation_steps: 2
|
| 42 |
+
- total_train_batch_size: 16
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 1000
|
| 46 |
+
- num_epochs: 20
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 52 |
+
| 3.12 | 1.05 | 250 | 3.3998 | 0.9982 |
|
| 53 |
+
| 3.0727 | 2.1 | 500 | 3.1261 | 0.9982 |
|
| 54 |
+
| 1.9729 | 3.15 | 750 | 1.4868 | 0.9464 |
|
| 55 |
+
| 1.3213 | 4.2 | 1000 | 1.2598 | 0.8833 |
|
| 56 |
+
| 1.0508 | 5.25 | 1250 | 1.0014 | 0.8102 |
|
| 57 |
+
| 0.8483 | 6.3 | 1500 | 0.9475 | 0.7944 |
|
| 58 |
+
| 0.7192 | 7.35 | 1750 | 0.9493 | 0.7686 |
|
| 59 |
+
| 0.6447 | 8.4 | 2000 | 0.9872 | 0.7573 |
|
| 60 |
+
| 0.6064 | 9.45 | 2250 | 0.9587 | 0.7447 |
|
| 61 |
+
| 0.5384 | 10.5 | 2500 | 0.9332 | 0.7320 |
|
| 62 |
+
| 0.4985 | 11.55 | 2750 | 0.9926 | 0.7315 |
|
| 63 |
+
| 0.4643 | 12.6 | 3000 | 1.0008 | 0.7292 |
|
| 64 |
+
| 0.4565 | 13.65 | 3250 | 0.9522 | 0.7171 |
|
| 65 |
+
| 0.449 | 14.7 | 3500 | 0.9685 | 0.7140 |
|
| 66 |
+
| 0.4307 | 15.75 | 3750 | 1.0080 | 0.7077 |
|
| 67 |
+
| 0.4239 | 16.81 | 4000 | 0.9950 | 0.7023 |
|
| 68 |
+
| 0.389 | 17.86 | 4250 | 1.0260 | 0.7007 |
|
| 69 |
+
| 0.3471 | 18.91 | 4500 | 1.0012 | 0.6966 |
|
| 70 |
+
| 0.3276 | 19.96 | 4750 | 1.0238 | 0.6969 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.17.0
|
| 76 |
+
- Pytorch 1.11.0+cu102
|
| 77 |
+
- Datasets 2.0.0
|
| 78 |
+
- Tokenizers 0.11.6
|