Downloads · 30 days
7
12% of all-time downloads
ls-timit-100percent-supervised-aug
Kuray107/ls-timit-100percent-supervised-aug
ls-timit-100percent-supervised-aug is a automatic speech recognition model from Kuray107. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
59
Public
Repo size
5 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
- Model type
- wav2vec2
- Access
- Public
- Created
- Apr 5, 2022
- Updated
- Apr 5, 2022
- SHA
- 98616405
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. -->
ls-timit-100percent-supervised-aug
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0519
- Wer: 0.0292
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: 0.0001
- train_batch_size: 32
- 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: 1000
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2985 | 7.04 | 1000 | 0.0556 | 0.0380 |
| 0.1718 | 14.08 | 2000 | 0.0519 | 0.0292 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2
- Datasets 1.18.2
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- Apr 5, 2022
- Updated
- Apr 5, 2022