Downloads · 30 days
7
14% of all-time downloads
wav2vec2-burak-new-300
burakyldrm/wav2vec2-burak-new-300
wav2vec2-burak-new-300 is a automatic speech recognition model from burakyldrm. 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
49
Public
Repo size
3.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Sep 13, 2022
- Updated
- Sep 14, 2022
- SHA
- 054c3101
Datasets
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-burak-new-300
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.5042
- Wer: 0.3803
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: 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: 500
- num_epochs: 41
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 4.7568 | 8.62 | 500 | 2.6689 | 1.0 |
| 0.7678 | 17.24 | 1000 | 0.5044 | 0.4656 |
| 0.2373 | 25.86 | 1500 | 0.4944 | 0.4047 |
| 0.1526 | 34.48 | 2000 | 0.5042 | 0.3803 |
Framework versions
- Transformers 4.21.3
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Sep 13, 2022
- Updated
- Sep 14, 2022