Downloads · 30 days
4
10% of all-time downloads
wav2vec2-base-commonvoice-demo-colab-2
chrisvinsen/wav2vec2-base-commonvoice-demo-colab-2
wav2vec2-base-commonvoice-demo-colab-2 is a automatic speech recognition model from chrisvinsen. 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
39
Public
Repo size
755 MB
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 16, 2022
- Updated
- Apr 16, 2022
- SHA
- 4af967b2
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-commonvoice-demo-colab-2
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: nan
- Wer: 1.0
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 |
|---|---|---|---|---|
| 4.7784 | 2.58 | 500 | 2.9962 | 1.0 |
| 3.0067 | 5.15 | 1000 | 3.0303 | 1.0 |
| 3.0098 | 7.73 | 1500 | 3.0305 | 1.0 |
| 3.0015 | 10.31 | 2000 | 3.0308 | 1.0 |
| 3.0062 | 12.89 | 2500 | 3.0310 | 1.0 |
| 3.0074 | 15.46 | 3000 | 3.0311 | 1.0 |
| 3.0085 | 18.04 | 3500 | 3.0313 | 1.0 |
| 3.0046 | 20.62 | 4000 | 3.0314 | 1.0 |
| 3.0065 | 23.2 | 4500 | nan | 1.0 |
| 0.0 | 25.77 | 5000 | nan | 1.0 |
| 0.0 | 28.35 | 5500 | nan | 1.0 |
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 16, 2022
- Updated
- Apr 16, 2022