metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-base-finetune-vi-v2
results: []
widget:
- example_title: SOICT 2023 - SLU public test 1
src: >-
https://huggingface.co/foxxy-hm/wav2vec2-base-finetune-vi/raw/main/audio-test/055R7BruAa333g9teFfamQH.wav
- example_title: SOICT 2023 - SLU public test 2
src: >-
https://huggingface.co/foxxy-hm/wav2vec2-base-finetune-vi/raw/main/audio-test/0BLHhoJexE8THB8BrsZxWbh.wav
- example_title: SOICT 2023 - SLU public test 3
src: >-
https://huggingface.co/foxxy-hm/wav2vec2-base-finetune-vi/raw/main/audio-test/1ArUTGWJQ9YALH2xaNhU6GV.wav
wav2vec2-base-finetune-vi-v2
This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vietnamese-250h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2294
- Wer: 0.1457
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 13.1354 | 0.67 | 500 | 3.0881 | 1.0186 |
| 2.2088 | 1.34 | 1000 | 0.9805 | 0.4257 |
| 1.122 | 2.0 | 1500 | 0.4928 | 0.2850 |
| 0.7567 | 2.67 | 2000 | 0.4217 | 0.2466 |
| 0.627 | 3.34 | 2500 | 0.3889 | 0.2212 |
| 0.5369 | 4.01 | 3000 | 0.3496 | 0.2131 |
| 0.4485 | 4.67 | 3500 | 0.3239 | 0.1994 |
| 0.4478 | 5.34 | 4000 | 0.3143 | 0.1944 |
| 0.4013 | 6.01 | 4500 | 0.2989 | 0.1871 |
| 0.4542 | 6.68 | 5000 | 0.2996 | 0.1871 |
| 0.351 | 7.34 | 5500 | 0.2719 | 0.1736 |
| 0.3236 | 8.01 | 6000 | 0.2865 | 0.1702 |
| 0.2954 | 8.68 | 6500 | 0.2708 | 0.1636 |
| 0.3533 | 9.35 | 7000 | 0.2712 | 0.1639 |
| 0.2996 | 10.01 | 7500 | 0.2609 | 0.1621 |
| 0.2595 | 10.68 | 8000 | 0.2450 | 0.1627 |
| 0.2914 | 11.35 | 8500 | 0.2748 | 0.1596 |
| 0.253 | 12.02 | 9000 | 0.2496 | 0.1552 |
| 0.2314 | 12.68 | 9500 | 0.2496 | 0.1549 |
| 0.2232 | 13.35 | 10000 | 0.2594 | 0.1557 |
| 0.2206 | 14.02 | 10500 | 0.2485 | 0.1529 |
| 0.2026 | 14.69 | 11000 | 0.2365 | 0.1522 |
| 0.2009 | 15.35 | 11500 | 0.2396 | 0.1513 |
| 0.205 | 16.02 | 12000 | 0.2433 | 0.1499 |
| 0.207 | 16.69 | 12500 | 0.2363 | 0.1496 |
| 0.1895 | 17.36 | 13000 | 0.2280 | 0.1481 |
| 0.1991 | 18.02 | 13500 | 0.2352 | 0.1481 |
| 0.2109 | 18.69 | 14000 | 0.2353 | 0.1477 |
| 0.1959 | 19.36 | 14500 | 0.2294 | 0.1457 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3