Downloads · 30 days
9
2% of all-time downloads
ai-light-dance_singing_ft_wav2vec2-large-xlsr-53
gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53
ai-light-dance_singing_ft_wav2vec2-large-xlsr-53 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
393
Public
Repo size
3.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jun 15, 2022
- Updated
- Jun 17, 2022
- SHA
- 64658180
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_singing_ft_wav2vec2-large-xlsr-53
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the GARY109/AI_LIGHT_DANCE - ONSET-SINGING dataset. It achieves the following results on the evaluation set:
- Loss: 0.4327
- Wer: 0.2043
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: 5e-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 |
|---|---|---|---|---|
| 1.4089 | 1.0 | 552 | 1.4750 | 0.9054 |
| 0.7995 | 2.0 | 1104 | 0.9044 | 0.6163 |
| 0.6232 | 3.0 | 1656 | 0.6645 | 0.3980 |
| 0.5351 | 4.0 | 2208 | 0.5674 | 0.3120 |
| 0.472 | 5.0 | 2760 | 0.5167 | 0.2579 |
| 0.3913 | 6.0 | 3312 | 0.4553 | 0.2335 |
| 0.3306 | 7.0 | 3864 | 0.4476 | 0.2114 |
| 0.3028 | 8.0 | 4416 | 0.4327 | 0.2043 |
| 0.317 | 9.0 | 4968 | 0.4355 | 0.2033 |
| 0.2494 | 10.0 | 5520 | 0.4405 | 0.2022 |
Framework versions
- Transformers 4.20.0.dev0
- Pytorch 1.11.0+cu113
- Datasets 2.3.1.dev0
- Tokenizers 0.12.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jun 15, 2022
- Updated
- Jun 17, 2022