Downloads · 30 days
3
1% of all-time downloads
wav2vec2-wer
adrianSauer/wav2vec2-wer
wav2vec2-wer is a automatic speech recognition model from adrianSauer. 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
239
Public
Parameters
315M
3.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Mar 16, 2024
- Updated
- Aug 18, 2024
- SHA
- 19652859
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. -->
Common Voice 16
This model is a fine-tuned version of glob-asr/wav2vec2-large-xls-r-300m-guarani-small on the Common Voice 16 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3513
- Wer: 49.7668
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4171 | 1.0152 | 100 | 0.3798 | 55.2965 |
| 0.3376 | 2.0305 | 200 | 0.3628 | 53.8974 |
| 0.294 | 3.0457 | 300 | 0.3528 | 52.4983 |
| 0.2632 | 4.0609 | 400 | 0.3484 | 49.7668 |
| 0.2459 | 5.0761 | 500 | 0.3513 | 49.7668 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- gn
- Created
- Mar 16, 2024
- Updated
- Aug 18, 2024