metadata
language:
- multilingual
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: model trenovan na en-de-en not simlar setu, nastaveni jazyka en
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: xbilek25/train_set_1st_1000_de_en_de
type: mozilla-foundation/common_voice_11_0
args: 'config: ende, split: train'
metrics:
- name: Wer
type: wer
value: 14.517374517374519
model trenovan na en-de-en not simlar setu, nastaveni jazyka en
This model is a fine-tuned version of openai/whisper-medium on the xbilek25/train_set_1st_1000_de_en_de dataset. It achieves the following results on the evaluation set:
- Loss: 0.3121
- Wer: 14.5174
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: 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: 1
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2582 | 0.1 | 200 | 0.2807 | 15.3153 |
| 0.0882 | 1.07 | 400 | 0.2688 | 14.0541 |
| 0.0293 | 2.05 | 600 | 0.2696 | 13.5907 |
| 0.0152 | 3.02 | 800 | 0.2752 | 13.8739 |
| 0.0106 | 3.12 | 1000 | 0.2862 | 13.9511 |
| 0.0046 | 4.1 | 1200 | 0.2895 | 13.5907 |
| 0.0023 | 5.08 | 1400 | 0.3044 | 14.3372 |
| 0.0023 | 6.05 | 1600 | 0.3060 | 14.1828 |
| 0.0016 | 7.03 | 1800 | 0.3100 | 14.3887 |
| 0.0015 | 7.12 | 2000 | 0.3121 | 14.5174 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2