ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v4
This model is a fine-tuned version of gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v2 on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING dataset. It achieves the following results on the evaluation set:
- Loss: 0.4231
- Wer: 0.1597
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: 4e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.1335 | 1.0 | 138 | 0.4256 | 0.1605 |
0.1288 | 2.0 | 276 | 0.4234 | 0.1602 |
0.1278 | 3.0 | 414 | 0.4243 | 0.1597 |
0.1345 | 4.0 | 552 | 0.4231 | 0.1597 |
0.1344 | 5.0 | 690 | 0.4246 | 0.1597 |
0.1237 | 6.0 | 828 | 0.4279 | 0.1595 |
0.1109 | 7.0 | 966 | 0.4354 | 0.1573 |
0.1247 | 8.0 | 1104 | 0.4318 | 0.1570 |
0.1372 | 9.0 | 1242 | 0.4341 | 0.1573 |
0.1256 | 10.0 | 1380 | 0.4328 | 0.1575 |
Framework versions
- Transformers 4.21.0.dev0
- Pytorch 1.9.1+cu102
- Datasets 2.3.3.dev0
- Tokenizers 0.12.1
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.