Downloads · 30 days
6
27% of all-time downloads
sereer-kallaama-15-mins
taiyintaiyang/sereer-kallaama-15-mins
sereer-kallaama-15-mins is a automatic speech recognition model from taiyintaiyang. 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
22
Public
Parameters
316M
13.9 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
- Dec 5, 2024
- Updated
- Dec 5, 2024
- SHA
- 1c8d2b46
Base models
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. -->
sereer-kallaama-15-mins
This model is a fine-tuned version of asr-africa/wav2vec2-xls-r-300m-Fleurs_AMMI_AFRIVOICE_LRSC-ln-100hrs-v2 on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.0482
- Wer: 0.8983
- Cer: 0.4414
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.5212 | 4.0 | 4 | 2.6957 | 1.0 | 0.9799 |
| 1.0473 | 8.0 | 8 | 2.0161 | 0.9288 | 0.4718 |
| 0.7149 | 12.0 | 12 | 2.6916 | 0.9525 | 0.4452 |
| 0.4837 | 16.0 | 16 | 1.8987 | 0.9153 | 0.4476 |
| 0.4144 | 20.0 | 20 | 2.0482 | 0.8983 | 0.4414 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Dec 5, 2024
- Updated
- Dec 5, 2024