Downloads · 30 days
5
2% of all-time downloads
wav2vec2-base-checkpoint-2
jiobiala24/wav2vec2-base-checkpoint-2
wav2vec2-base-checkpoint-2 is a automatic speech recognition model from jiobiala24. 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
310
Public
Repo size
2.3 GB
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
- Mar 2, 2022
- Updated
- Jan 7, 2022
- SHA
- e236f84d
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-base-TPU-cv-fine-tune-2
This model is a fine-tuned version of jiobiala24/wav2vec2-base-TPU-cv-fine-tune on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 1.6051
- Wer: 0.5484
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.522 | 6.45 | 400 | 1.2550 | 0.5649 |
| 0.2874 | 12.9 | 800 | 1.4235 | 0.6054 |
| 0.152 | 19.35 | 1200 | 1.5743 | 0.5806 |
| 0.0857 | 25.8 | 1600 | 1.6051 | 0.5484 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.13.3
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Mar 2, 2022
- Updated
- Jan 7, 2022