Downloads · 30 days
4
9% of all-time downloads
wav2vec2-base-timit-demo-colab3
obokkkk/wav2vec2-base-timit-demo-colab3
wav2vec2-base-timit-demo-colab3 is a automatic speech recognition model from obokkkk. 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
45
Public
Repo size
1.5 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
- Apr 21, 2022
- Updated
- Apr 21, 2022
- SHA
- 3946e181
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-colab3
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: 0.4832
- Wer: 0.3419
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: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.292 | 4.0 | 500 | 0.7903 | 0.6305 |
| 0.5022 | 8.0 | 1000 | 0.4497 | 0.4332 |
| 0.2129 | 12.0 | 1500 | 0.4998 | 0.3940 |
| 0.1251 | 16.0 | 2000 | 0.4728 | 0.3667 |
| 0.0861 | 20.0 | 2500 | 0.4663 | 0.3644 |
| 0.0594 | 24.0 | 3000 | 0.4773 | 0.3497 |
| 0.0446 | 28.0 | 3500 | 0.4832 | 0.3419 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Apr 21, 2022
- Updated
- Apr 21, 2022