Downloads · 30 days
7
22% of all-time downloads
whisper-mit
tfbghjk/whisper-mit
whisper-mit is a automatic speech recognition model from tfbghjk. 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
32
Public
Parameters
242M
967 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jun 1, 2025
- Updated
- Jun 1, 2025
- SHA
- cabc9432
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-mit
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1383
- Wer: 0.0956
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: 5e-06
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- 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: 50
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7358 | 1.0 | 56 | 0.3125 | 0.1086 |
| 0.2782 | 2.0 | 112 | 0.2306 | 0.1030 |
| 0.2008 | 3.0 | 168 | 0.1942 | 0.1022 |
| 0.1519 | 4.0 | 224 | 0.1633 | 0.0969 |
| 0.1093 | 5.0 | 280 | 0.1383 | 0.0956 |
| 0.0694 | 6.0 | 336 | 0.1368 | 0.0971 |
| 0.0484 | 7.0 | 392 | 0.1451 | 0.1454 |
Framework versions
- Transformers 4.52.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jun 1, 2025
- Updated
- Jun 1, 2025