metadata
language:
- sq
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- CV_Albanian
model-index:
- name: Whisper Medium CV Test
results: []
Whisper Medium CV Test
This model is a fine-tuned version of openai/whisper-medium on the CV Albanian dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.7844
- eval_wer: 39.9593
- eval_runtime: 186.4098
- eval_samples_per_second: 2.06
- eval_steps_per_second: 0.257
- epoch: 37.04
- step: 2000
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0338 | 0.2 | 500 | 0.7342 | 45.9470 |
| 0.0026 | 0.4 | 1000 | 0.7724 | 40.4887 |
| 0.0008 | 0.8 | 1500 | 0.7513 | 39.7148 |
| 0.0001 | 1.0 | 2000 | 0.7844 | 39.9592 |
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: 5000
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2