Downloads · 30 days
13
28% of all-time downloads
whisper-small-marathi-fine-tuned
simran14/whisper-small-marathi-fine-tuned
whisper-small-marathi-fine-tuned is a automatic speech recognition model from simran14. 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
47
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
- Jul 7, 2024
- Updated
- Jul 12, 2024
- SHA
- d0c39fdb
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. -->
simrank14 whisper small marathi fine-tuned
This model is a fine-tuned version of [simran14/mr-small-whisper-oi](https://huggingface.co/simran14/Whisper Small marathi fine-tuned) on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3276
- Wer: 12.7884
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0003 | 2.6714 | 3000 | 0.3276 | 12.7884 |
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- mr
- Created
- Jul 7, 2024
- Updated
- Jul 12, 2024