Downloads · 30 days
17
12% of all-time downloads
medasr-ghana-v2
samwell/medasr-ghana-v2
medasr-ghana-v2 is a automatic speech recognition model from samwell. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
143
Public
Parameters
105M
6.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt842 MB · 50%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- other
- Model type
- lasr_ctc
- Access
- Public
- Created
- Jan 20, 2026
- Updated
- Jan 20, 2026
- SHA
- 8e7425fa
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. -->
medasr-ghana-v2
This model is a fine-tuned version of google/medasr on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1764
- Wer: 0.4116
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- 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: 19
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 85.5056 | 7.1527 | 100 | 2.2687 | 0.5682 |
| 71.0330 | 14.3055 | 200 | 1.9314 | 0.5153 |
| 69.0262 | 21.4582 | 300 | 1.8050 | 0.5015 |
| 66.9954 | 28.6110 | 400 | 1.7908 | 0.4932 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.1+cu128
- Datasets 2.20.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- lasr_ctc
- License
- other
- Created
- Jan 20, 2026
- Updated
- Jan 20, 2026