<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
wav2vec2-baseline
This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vi on the QUOCANH34/ASR_SPOKEN_NORM_TRAIN_DATA - NA dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Wer: 1.0
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: 8e-06
- train_batch_size: 32
- 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: 500
- num_epochs: 30.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.43 | 100 | inf | 1.2580 |
| No log | 0.85 | 200 | inf | 1.0 |
| No log | 1.28 | 300 | inf | 1.0 |
| No log | 1.71 | 400 | inf | 1.0 |
| 12.36 | 2.14 | 500 | inf | 1.0 |
| 12.36 | 2.56 | 600 | inf | 1.0 |
| 12.36 | 2.99 | 700 | inf | 1.0 |
| 12.36 | 3.42 | 800 | inf | 1.0 |
| 12.36 | 3.85 | 900 | inf | 1.0 |
| 8.4674 | 4.27 | 1000 | inf | 1.0 |
| 8.4674 | 4.7 | 1100 | inf | 1.0 |
| 8.4674 | 5.13 | 1200 | inf | 1.0 |
| 8.4674 | 5.56 | 1300 | inf | 1.0 |
| 8.4674 | 5.98 | 1400 | inf | 1.0 |
| 6.9866 | 6.41 | 1500 | inf | 1.0 |
| 6.9866 | 6.84 | 1600 | inf | 1.0 |
| 6.9866 | 7.26 | 1700 | inf | 1.0 |
| 6.9866 | 7.69 | 1800 | inf | 1.0 |
| 6.9866 | 8.12 | 1900 | inf | 1.0 |
| 6.8089 | 8.55 | 2000 | inf | 1.0 |
| 6.8089 | 8.97 | 2100 | inf | 1.0 |
| 6.8089 | 9.4 | 2200 | inf | 1.0 |
| 6.8089 | 9.83 | 2300 | inf | 1.0 |
| 6.8089 | 10.26 | 2400 | inf | 1.0 |
| 6.7847 | 10.68 | 2500 | inf | 1.0 |
| 6.7847 | 11.11 | 2600 | inf | 1.0 |
| 6.7847 | 11.54 | 2700 | inf | 1.0 |
| 6.7847 | 11.97 | 2800 | inf | 1.0 |
| 6.7847 | 12.39 | 2900 | inf | 1.0 |
| 6.7941 | 12.82 | 3000 | inf | 1.0 |
| 6.7941 | 13.25 | 3100 | inf | 1.0 |
| 6.7941 | 13.68 | 3200 | inf | 1.0 |
| 6.7941 | 14.1 | 3300 | inf | 1.0 |
| 6.7941 | 14.53 | 3400 | inf | 1.0 |
| 6.7956 | 14.96 | 3500 | inf | 1.0 |
| 6.7956 | 15.38 | 3600 | inf | 1.0 |
| 6.7956 | 15.81 | 3700 | inf | 1.0 |
| 6.7956 | 16.24 | 3800 | inf | 1.0 |
| 6.7956 | 16.67 | 3900 | inf | 1.0 |
| 6.8102 | 17.09 | 4000 | inf | 1.0 |
| 6.8102 | 17.52 | 4100 | inf | 1.0 |
| 6.8102 | 17.95 | 4200 | inf | 1.0 |
| 6.8102 | 18.38 | 4300 | inf | 1.0 |
| 6.8102 | 18.8 | 4400 | inf | 1.0 |
| 6.7761 | 19.23 | 4500 | inf | 1.0 |
| 6.7761 | 19.66 | 4600 | inf | 1.0 |
| 6.7761 | 20.09 | 4700 | inf | 1.0 |
| 6.7761 | 20.51 | 4800 | inf | 1.0 |
| 6.7761 | 20.94 | 4900 | inf | 1.0 |
| 6.8063 | 21.37 | 5000 | inf | 1.0 |
| 6.8063 | 21.79 | 5100 | inf | 1.0 |
| 6.8063 | 22.22 | 5200 | inf | 1.0 |
| 6.8063 | 22.65 | 5300 | inf | 1.0 |
| 6.8063 | 23.08 | 5400 | inf | 1.0 |
| 6.7934 | 23.5 | 5500 | inf | 1.0 |
| 6.7934 | 23.93 | 5600 | inf | 1.0 |
| 6.7934 | 24.36 | 5700 | inf | 1.0 |
| 6.7934 | 24.79 | 5800 | inf | 1.0 |
| 6.7934 | 25.21 | 5900 | inf | 1.0 |
| 6.7819 | 25.64 | 6000 | inf | 1.0 |
| 6.7819 | 26.07 | 6100 | inf | 1.0 |
| 6.7819 | 26.5 | 6200 | inf | 1.0 |
| 6.7819 | 26.92 | 6300 | inf | 1.0 |
| 6.7819 | 27.35 | 6400 | inf | 1.0 |
| 6.8278 | 27.78 | 6500 | inf | 1.0 |
| 6.8278 | 28.21 | 6600 | inf | 1.0 |
| 6.8278 | 28.63 | 6700 | inf | 1.0 |
| 6.8278 | 29.06 | 6800 | nan | 1.0 |
| 6.8278 | 29.49 | 6900 | nan | 1.0 |
| 6.7427 | 29.91 | 7000 | nan | 1.0 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
