Downloads · 30 days
5
23% of all-time downloads
whisper-welsh
nourfahmy/whisper-welsh
whisper-welsh is a automatic speech recognition model from nourfahmy. 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
72.6M
290 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors290 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026
- SHA
- dbea96fe
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. -->
whisper-welsh
This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0702
- Wer: 0.6419
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.1568 | 1.6420 | 200 | 1.2531 | 0.7304 |
| 2.5815 | 3.2798 | 400 | 1.1026 | 0.6627 |
| 2.4989 | 4.9218 | 600 | 1.0702 | 0.6419 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026