Downloads · 30 days
19
1% of all-time downloads
whisper-small-hy-AM
Chillarmo/whisper-small-hy-AM
whisper-small-hy-AM is a automatic speech recognition model from Chillarmo. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
Chillarmo/whisper-small-hy-AM is an AI model designed for speech-to-text conversion specifically tailored for the Armenian language. Leveraging the power of fine-tuning, this model, named whisper-small-hy-AM, is based…
All-time downloads
1.4K
Public
Parameters
242M
3.9 GB on disk
Likes
3
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
- Feb 7, 2024
- Updated
- Feb 10, 2024
- SHA
- 6bd668d8
Base models
Model card
From the Hugging Face model README
Model description
Chillarmo/whisper-small-hy-AM is an AI model designed for speech-to-text conversion specifically tailored for the Armenian language. Leveraging the power of fine-tuning, this model, named whisper-small-hy-AM, is based on openai/whisper-small and trained on the common_voice_16_1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2853
- Wer: 38.1160
Training Data and Future Enhancements
The training data consists of Mozilla Common Voice version 16.1. Plans for future improvements include continuing the training process and integrating an additional 10 hours of data from datasets such as google/fleurs and possibly google/xtreme_s. Despite its current performance, efforts are underway to further reduce the WER.
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: 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
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0989 | 2.48 | 1000 | 0.1948 | 41.5758 |
| 0.03 | 4.95 | 2000 | 0.2165 | 39.1251 |
| 0.0016 | 7.43 | 3000 | 0.2659 | 38.4089 |
| 0.0005 | 9.9 | 4000 | 0.2853 | 38.1160 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- hy
- Created
- Feb 7, 2024
- Updated
- Feb 10, 2024