Downloads · 30 days
10
2% of all-time downloads
wav2vec2-base-demo-colab
eaqui/wav2vec2-base-demo-colab
wav2vec2-base-demo-colab is a automatic speech recognition model from eaqui. 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
405
Public
Repo size
2.3 GB
Likes
1
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
- Dec 27, 2022
- Updated
- Dec 28, 2022
- SHA
- 9a34fc35
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-demo-colab
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: 0.4409
- Wer: 0.3484
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: 8
- 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: 12
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.3824 | 1.0 | 500 | 1.4646 | 1.0050 |
| 0.8251 | 2.01 | 1000 | 0.5555 | 0.5319 |
| 0.4265 | 3.01 | 1500 | 0.4303 | 0.4456 |
| 0.2864 | 4.02 | 2000 | 0.4605 | 0.4284 |
| 0.2124 | 5.02 | 2500 | 0.3851 | 0.3862 |
| 0.1658 | 6.02 | 3000 | 0.3870 | 0.3815 |
| 0.136 | 7.03 | 3500 | 0.4154 | 0.3726 |
| 0.1124 | 8.03 | 4000 | 0.4399 | 0.3642 |
| 0.0943 | 9.04 | 4500 | 0.4069 | 0.3544 |
| 0.0772 | 10.04 | 5000 | 0.4544 | 0.3539 |
| 0.066 | 11.04 | 5500 | 0.4409 | 0.3484 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Dec 27, 2022
- Updated
- Dec 28, 2022