README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1
    results: []

ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1

This model is a fine-tuned version of gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6009
• Wer: 0.3386

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: 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: 100
• num_epochs: 20.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.6364	1.0	578	0.6806	0.4167
0.6466	2.0	1156	0.7114	0.4238
0.6371	3.0	1734	0.7033	0.4318
0.7171	4.0	2312	0.6488	0.3970
0.6228	5.0	2890	0.6369	0.3858
0.6004	6.0	3468	0.6313	0.4088
0.6074	7.0	4046	0.6295	0.3794
0.6075	8.0	4624	0.6280	0.3692
0.5936	9.0	5202	0.6201	0.3648
0.5737	10.0	5780	0.6289	0.3512
0.5711	11.0	6358	0.6288	0.3545
0.5617	12.0	6936	0.6308	0.3662
0.5796	13.0	7514	0.6088	0.3546
0.5401	14.0	8092	0.6190	0.3488
0.5137	15.0	8670	0.6050	0.3397
0.5038	16.0	9248	0.6019	0.3414
0.5303	17.0	9826	0.6061	0.3456
0.5401	18.0	10404	0.6051	0.3410
0.5394	19.0	10982	0.6061	0.3399
0.4707	20.0	11560	0.6009	0.3386

Framework versions

• Transformers 4.21.0.dev0
• Pytorch 1.9.1+cu102
• Datasets 2.3.3.dev0
• Tokenizers 0.12.1