Automatic Speech Recognition
Transformers
PyTorch
Armenian
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("arampacha/whisper-large-hy")
model = AutoModelForSpeechSeq2Seq.from_pretrained("arampacha/whisper-large-hy")Quick Links
whisper-large-hy
This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2204
- Wer: 22.3684
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1394 | 5.87 | 400 | 0.1780 | 28.2895 |
| 0.0536 | 11.75 | 800 | 0.1739 | 24.6053 |
| 0.0247 | 17.64 | 1200 | 0.2098 | 22.9605 |
| 0.0154 | 23.52 | 1600 | 0.2035 | 22.1382 |
| 0.0103 | 29.41 | 2000 | 0.2204 | 22.3684 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 21
Dataset used to train arampacha/whisper-large-hy
Evaluation results
- Wer on Common Voice 11.0test set self-reported22.368
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="arampacha/whisper-large-hy")