ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v2
This model is a fine-tuned version of gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram-v1 on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING dataset. It achieves the following results on the evaluation set:
- Loss: 0.4313
- Wer: 0.1645
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.148 | 1.0 | 552 | 0.4313 | 0.1645 |
0.1301 | 2.0 | 1104 | 0.4365 | 0.1618 |
0.1237 | 3.0 | 1656 | 0.4470 | 0.1595 |
0.1063 | 4.0 | 2208 | 0.4593 | 0.1576 |
0.128 | 5.0 | 2760 | 0.4525 | 0.1601 |
0.1099 | 6.0 | 3312 | 0.4593 | 0.1567 |
0.0969 | 7.0 | 3864 | 0.4625 | 0.1550 |
0.0994 | 8.0 | 4416 | 0.4672 | 0.1543 |
0.125 | 9.0 | 4968 | 0.4636 | 0.1544 |
0.0887 | 10.0 | 5520 | 0.4601 | 0.1538 |
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.