Downloads · 30 days
5
1% of all-time downloads
wav2vec2-colab
Nithiwat/wav2vec2-colab
wav2vec2-colab is a automatic speech recognition model from Nithiwat. 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
383
Public
Repo size
6.3 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
- Jan 3, 2023
- Updated
- Jan 8, 2023
- SHA
- 524741b4
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-colab
This model is a fine-tuned version of facebook/wav2vec2-xlsr-53-espeak-cv-ft on the None dataset. It achieves the following results on the evaluation set:
- Loss: inf
- Wer: 0.9155
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: 5e-06
- train_batch_size: 24
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7628 | 7.83 | 400 | inf | 0.9155 |
| 1.0544 | 15.68 | 800 | inf | 0.9155 |
| 7.5478 | 23.52 | 1200 | inf | 0.9155 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.10.0+cu113
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jan 3, 2023
- Updated
- Jan 8, 2023