Downloads · 30 days
5
1% of all-time downloads
wav2vec2-base-timit-demo-colab-1
zasheza/wav2vec2-base-timit-demo-colab-1
wav2vec2-base-timit-demo-colab-1 is a automatic speech recognition model from zasheza. 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
425
Public
Repo size
3.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- May 1, 2022
- Updated
- May 1, 2022
- SHA
- 180c9772
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. -->
wav2vec2-base-timit-demo-colab-1
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9634
- Wer: 0.4398
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: 0.0002
- train_batch_size: 6
- 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: 800
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.8991 | 5.26 | 500 | 1.4319 | 0.7522 |
| 0.8555 | 10.53 | 1000 | 0.7895 | 0.5818 |
| 0.4584 | 15.79 | 1500 | 0.7198 | 0.5211 |
| 0.3096 | 21.05 | 2000 | 0.7983 | 0.5118 |
| 0.2165 | 26.32 | 2500 | 0.7893 | 0.4745 |
| 0.163 | 31.58 | 3000 | 0.8779 | 0.4589 |
| 0.1144 | 36.84 | 3500 | 0.9256 | 0.4540 |
| 0.0886 | 42.11 | 4000 | 0.9184 | 0.4530 |
| 0.0668 | 47.37 | 4500 | 0.9634 | 0.4398 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.11.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- May 1, 2022
- Updated
- May 1, 2022