Commit
·
14b74e2
1
Parent(s):
704ce38
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 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-speech-project-subsetData
|
| 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-speech-project-subsetData
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1157
|
| 20 |
+
- Wer: 0.2453
|
| 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: 0.0001
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 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: 30
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 14.9506 | 1.67 | 50 | 16.5714 | 1.0 |
|
| 54 |
+
| 7.9883 | 3.33 | 100 | 4.1299 | 1.0 |
|
| 55 |
+
| 3.4027 | 5.0 | 150 | 3.2576 | 1.0 |
|
| 56 |
+
| 3.1425 | 6.67 | 200 | 3.0644 | 1.0 |
|
| 57 |
+
| 3.0198 | 8.33 | 250 | 2.9955 | 1.0 |
|
| 58 |
+
| 2.974 | 10.0 | 300 | 2.9685 | 1.0 |
|
| 59 |
+
| 2.9492 | 11.67 | 350 | 2.9520 | 1.0 |
|
| 60 |
+
| 2.9225 | 13.33 | 400 | 3.0013 | 1.0 |
|
| 61 |
+
| 2.8383 | 15.0 | 450 | 2.7433 | 1.0 |
|
| 62 |
+
| 2.5389 | 16.67 | 500 | 2.1815 | 1.0 |
|
| 63 |
+
| 1.8402 | 18.33 | 550 | 1.2757 | 0.9653 |
|
| 64 |
+
| 0.926 | 20.0 | 600 | 0.4806 | 0.4453 |
|
| 65 |
+
| 0.4593 | 21.67 | 650 | 0.3497 | 0.376 |
|
| 66 |
+
| 0.3047 | 23.33 | 700 | 0.1765 | 0.2507 |
|
| 67 |
+
| 0.2407 | 25.0 | 750 | 0.1152 | 0.216 |
|
| 68 |
+
| 0.1867 | 26.67 | 800 | 0.2214 | 0.2987 |
|
| 69 |
+
| 0.1637 | 28.33 | 850 | 0.1050 | 0.2453 |
|
| 70 |
+
| 0.1599 | 30.0 | 900 | 0.1157 | 0.2453 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.28.1
|
| 76 |
+
- Pytorch 2.0.0+cu118
|
| 77 |
+
- Datasets 1.18.3
|
| 78 |
+
- Tokenizers 0.13.3
|