Downloads · 30 days
9
1% of all-time downloads
whisper-small-ml-imasc
thennal/whisper-small-ml-imasc
whisper-small-ml-imasc is a automatic speech recognition model from thennal. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
This model is a fine-tuned version of openai/whisper-small on the ICFOSS Malayalam Speech Corpus dataset. It achieves the following results on the evaluation set: - Loss: 0.0244 - Wer: 10.9459 - Cer: 1.7890
All-time downloads
876
Public
Repo size
17.4 GB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 6, 2022
- Updated
- Dec 11, 2022
- SHA
- 1670508a
Datasets
Model card
From the Hugging Face model README
Whisper Small Ml - IMaSC
This model is a fine-tuned version of openai/whisper-small on the ICFOSS Malayalam Speech Corpus dataset. It achieves the following results on the evaluation set:
- Loss: 0.0244
- Wer: 10.9459
- Cer: 1.7890
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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- ml
- Created
- Dec 6, 2022
- Updated
- Dec 11, 2022