Whisper Large-v2 Armenian
This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 hy-AM dataset. It achieves the following results on the evaluation set:
- Loss: 0.4429
- Wer: 40.2303
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: 32
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0113 | 8.02 | 200 | 0.3501 | 43.7171 |
| 0.0003 | 17.01 | 400 | 0.3989 | 40.7895 |
| 0.0001 | 26.0 | 600 | 0.4282 | 40.4605 |
| 0.0001 | 34.02 | 800 | 0.4392 | 40.2632 |
| 0.0001 | 43.01 | 1000 | 0.4429 | 40.2303 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 12
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train anuragshas/whisper-large-v2-hy
Evaluation results
- Wer on mozilla-foundation/common_voice_11_0 hy-AMtest set self-reported40.230