Downloads · 30 days
9
6% of all-time downloads
cdli-whisper-lg-sunbird-encoder-a40
KasuleTrevor/cdli-whisper-lg-sunbird-encoder-a40
cdli-whisper-lg-sunbird-encoder-a40 is a automatic speech recognition model from KasuleTrevor. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
151
Public
Parameters
1.5B
16.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 GB · 71%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- Apr 23, 2026
- Updated
- Apr 29, 2026
- SHA
- d610fd2b
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. -->
cdli-whisper-lg-sunbird-encoder-a40
This model is a fine-tuned version of Sunbird/asr-whisper-large-v3-salt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8208
- Wer: 0.6022
- Cer: 0.3259
- test_cer: 0.15645290229147257
- test_wer: 0.4013357258930758
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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: 500
- training_steps: 1500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.7453 | 1.3556 | 500 | 0.8565 | 0.6086 | 0.3192 |
| 0.7308 | 2.7112 | 1000 | 0.8233 | 0.6103 | 0.3305 |
| 0.6926 | 4.0652 | 1500 | 0.8208 | 0.6022 | 0.3259 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.21.4
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- mit
- Created
- Apr 23, 2026
- Updated
- Apr 29, 2026