metadata
language:
- cs
license: apache-2.0
tags:
- whisper-event
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
base_model: openai/whisper-medium
model-index:
- name: Whisper Medium Czech 2 CV11
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: mozilla-foundation/common_voice_11_0
type: mozilla-foundation/common_voice_11_0
config: cs
split: test
metrics:
- type: wer
value: 11.408629675328264
name: Wer
Whisper Medium Czech 2 CV11
This model is a fine-tuned version of openai/whisper-medium on the mozilla-foundation/common_voice_11_0 cs dataset. It achieves the following results on the evaluation set:
- Loss: 0.2417
- Wer: 11.4086
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: 32
- seed: 42
- gradient_accumulation_steps: 2
- 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0105 | 4.24 | 1000 | 0.1973 | 12.6130 |
| 0.0016 | 8.47 | 2000 | 0.2198 | 11.8985 |
| 0.0004 | 12.71 | 3000 | 0.2310 | 11.4547 |
| 0.0003 | 16.95 | 4000 | 0.2380 | 11.4270 |
| 0.0002 | 21.19 | 5000 | 0.2417 | 11.4086 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2