Commit
•
6e61943
1
Parent(s):
d4ccf4e
Upload 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: wav2vec2-19
|
| 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 |
+
# wav2vec2-19
|
| 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: 0.6305
|
| 18 |
+
- Wer: 0.4499
|
| 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: 0.0003
|
| 38 |
+
- train_batch_size: 32
|
| 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: 800
|
| 44 |
+
- num_epochs: 60
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 50 |
+
| 3.4816 | 2.74 | 400 | 1.0717 | 0.8927 |
|
| 51 |
+
| 0.751 | 5.48 | 800 | 0.7155 | 0.7533 |
|
| 52 |
+
| 0.517 | 8.22 | 1200 | 0.7039 | 0.6675 |
|
| 53 |
+
| 0.3988 | 10.96 | 1600 | 0.5935 | 0.6149 |
|
| 54 |
+
| 0.3179 | 13.7 | 2000 | 0.6477 | 0.5999 |
|
| 55 |
+
| 0.2755 | 16.44 | 2400 | 0.5549 | 0.5798 |
|
| 56 |
+
| 0.2343 | 19.18 | 2800 | 0.6626 | 0.5798 |
|
| 57 |
+
| 0.2103 | 21.92 | 3200 | 0.6488 | 0.5674 |
|
| 58 |
+
| 0.1877 | 24.66 | 3600 | 0.5874 | 0.5339 |
|
| 59 |
+
| 0.1719 | 27.4 | 4000 | 0.6354 | 0.5389 |
|
| 60 |
+
| 0.1603 | 30.14 | 4400 | 0.6612 | 0.5210 |
|
| 61 |
+
| 0.1401 | 32.88 | 4800 | 0.6676 | 0.5131 |
|
| 62 |
+
| 0.1286 | 35.62 | 5200 | 0.6366 | 0.5075 |
|
| 63 |
+
| 0.1159 | 38.36 | 5600 | 0.6064 | 0.4977 |
|
| 64 |
+
| 0.1084 | 41.1 | 6000 | 0.6530 | 0.4835 |
|
| 65 |
+
| 0.0974 | 43.84 | 6400 | 0.6118 | 0.4853 |
|
| 66 |
+
| 0.0879 | 46.58 | 6800 | 0.6316 | 0.4770 |
|
| 67 |
+
| 0.0815 | 49.32 | 7200 | 0.6125 | 0.4664 |
|
| 68 |
+
| 0.0708 | 52.05 | 7600 | 0.6449 | 0.4683 |
|
| 69 |
+
| 0.0651 | 54.79 | 8000 | 0.6068 | 0.4571 |
|
| 70 |
+
| 0.0555 | 57.53 | 8400 | 0.6305 | 0.4499 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.19.2
|
| 76 |
+
- Pytorch 1.11.0+cu113
|
| 77 |
+
- Datasets 2.2.2
|
| 78 |
+
- Tokenizers 0.12.1
|