Downloads · 30 days
6
1% of all-time downloads
ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v4
gary109/ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v4
ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v4 is a automatic speech recognition model from gary109. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
441
Public
Repo size
3.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jun 26, 2022
- Updated
- Jun 27, 2022
- SHA
- 6328e5e4
Model card
From the Hugging Face model README
<!-- 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. -->
ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v4
This model is a fine-tuned version of gary109/ai-light-dance_stepmania_ft_wav2vec2-large-xlsr-53-v3 on the GARY109/AI_LIGHT_DANCE - ONSET-STEPMANIA2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0298
- Wer: 0.6642
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: 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: 100
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.9218 | 1.0 | 188 | 1.0718 | 0.6958 |
| 0.9194 | 2.0 | 376 | 1.0354 | 0.6937 |
| 0.9077 | 3.0 | 564 | 1.0365 | 0.6730 |
| 0.8956 | 4.0 | 752 | 1.0497 | 0.6727 |
| 0.877 | 5.0 | 940 | 1.0299 | 0.6694 |
| 0.8736 | 6.0 | 1128 | 1.0298 | 0.6642 |
| 0.8769 | 7.0 | 1316 | 1.0348 | 0.6584 |
| 0.8571 | 8.0 | 1504 | 1.0689 | 0.6602 |
| 0.8573 | 9.0 | 1692 | 1.0559 | 0.6549 |
| 0.8458 | 10.0 | 1880 | 1.0706 | 0.6588 |
Framework versions
- Transformers 4.21.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.3.3.dev0
- Tokenizers 0.12.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jun 26, 2022
- Updated
- Jun 27, 2022