Downloads · 30 days
4
17% of all-time downloads
whisper-medium-v2-capstone
Alsman68/whisper-medium-v2-capstone
whisper-medium-v2-capstone is a automatic speech recognition model from Alsman68. 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
24
Public
Parameters
764M
12.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- whisper
- Access
- Public
- Created
- Feb 4, 2025
- Updated
- Feb 5, 2025
- SHA
- 9732a36c
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. -->
Whisper Medium for Capstone
This model is a fine-tuned version of openai/whisper-medium-v2 on the Trelis LLM Lingo dataset. It achieves the following results on the evaluation set:
- Loss: 1.9669
- Wer: 35.0467
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
- optimizer: Use OptimizerNames.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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0 | 1000.0 | 1000 | 1.7574 | 32.2430 |
| 0.0 | 2000.0 | 2000 | 1.8340 | 32.2430 |
| 0.0 | 3000.0 | 3000 | 1.9354 | 34.5794 |
| 0.0 | 4000.0 | 4000 | 1.9669 | 35.0467 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.0.1+cu117
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- Languages
- en
- Created
- Feb 4, 2025
- Updated
- Feb 5, 2025