Downloads · 30 days
6
18% of all-time downloads
wav2vec2_base_2
Myriam123/wav2vec2_base_2
wav2vec2_base_2 is a automatic speech recognition model from Myriam123. 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
34
Public
Parameters
94.4M
15.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Apr 27, 2024
- Updated
- Jun 12, 2024
- SHA
- 8c5208e0
Base models
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_2
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3557
- Wer: 0.7608
- Cer: 0.3063
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: 16
- 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: 500
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 3.076 | 5.8824 | 700 | 2.4260 | 1.0 | 0.9293 |
| 1.8231 | 11.7647 | 1400 | 1.3243 | 0.8707 | 0.3825 |
| 1.2424 | 17.6471 | 2100 | 1.2663 | 0.8147 | 0.3457 |
| 1.0114 | 23.5294 | 2800 | 1.2739 | 0.7913 | 0.3284 |
| 0.8612 | 29.4118 | 3500 | 1.2724 | 0.7880 | 0.3195 |
| 0.7902 | 35.2941 | 4200 | 1.3444 | 0.7730 | 0.3142 |
| 0.7041 | 41.1765 | 4900 | 1.3494 | 0.7592 | 0.3068 |
| 0.6675 | 47.0588 | 5600 | 1.3557 | 0.7608 | 0.3063 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Apr 27, 2024
- Updated
- Jun 12, 2024