Downloads · 30 days
15
5% of all-time downloads
tamasheq-99-new-data
ad019el/tamasheq-99-new-data
tamasheq-99-new-data is a automatic speech recognition model from ad019el. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
274
Public
Repo size
7.6 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
- Model type
- wav2vec2
- Access
- Public
- Created
- Aug 26, 2023
- Updated
- Aug 26, 2023
- SHA
- 6d0acbfc
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. -->
tamasheq-99-new-data
This model is a fine-tuned version of ad019el/tamasheq-99-final on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4502
- Wer: 0.5910
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: 3e-05
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.4543 | 9.8 | 500 | 0.8448 | 0.7354 |
| 0.3588 | 19.61 | 1000 | 0.4527 | 0.6020 |
| 0.2012 | 29.41 | 1500 | 0.4490 | 0.5950 |
| 0.1739 | 39.22 | 2000 | 0.4547 | 0.5950 |
| 0.1634 | 49.02 | 2500 | 0.4502 | 0.5910 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- Aug 26, 2023
- Updated
- Aug 26, 2023