ai-light-dance_singing2_ft_wav2vec2-large-xlsr-53-5gram-v3
This model is a fine-tuned version of gary109/ai-light-dance_singing2_ft_wav2vec2-large-xlsr-53-v2 on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5265
- Wer: 0.2256
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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.2546 | 1.0 | 280 | 0.6004 | 0.2796 |
0.2325 | 2.0 | 560 | 0.6337 | 0.2729 |
0.2185 | 3.0 | 840 | 0.5546 | 0.2299 |
0.1988 | 4.0 | 1120 | 0.5265 | 0.2256 |
0.1755 | 5.0 | 1400 | 0.5577 | 0.2212 |
0.1474 | 6.0 | 1680 | 0.6353 | 0.2241 |
0.1498 | 7.0 | 1960 | 0.5758 | 0.2086 |
0.1252 | 8.0 | 2240 | 0.5738 | 0.2052 |
0.1174 | 9.0 | 2520 | 0.5994 | 0.2048 |
0.1035 | 10.0 | 2800 | 0.5988 | 0.2038 |
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.