Downloads · 30 days
10
11% of all-time downloads
daniel_whisper_finetune_medium_v2
danielrosehill/daniel_whisper_finetune_medium_v2
daniel_whisper_finetune_medium_v2 is a automatic speech recognition model from danielrosehill. 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
93
Public
Parameters
764M
14.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin5 GB · 62%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 21, 2025
- Updated
- Nov 23, 2025
- SHA
- 4e1a4a69
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. -->
daniel_whisper_finetune_medium_v2
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1799
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 50
- training_steps: 250
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1622 | 1.3158 | 50 | 0.4810 |
| 0.06 | 2.6316 | 100 | 0.1686 |
| 0.0207 | 3.9474 | 150 | 0.1639 |
| 0.0078 | 5.2632 | 200 | 0.1709 |
| 0.0036 | 6.5789 | 250 | 0.1799 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Nov 21, 2025
- Updated
- Nov 23, 2025