metadata

language:
  - tr
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: stann-speechtotext-medium-tr-03_06
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: tr
          split: None
          args: tr
        metrics:
          - name: Wer
            type: wer
            value: 32.78548922762497

stann-speechtotext-medium-tr-03_06

This model is a fine-tuned version of openai/whisper-medium on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

Loss: 0.2244
Wer: 32.7855

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
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: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0307	1.3784	1000	0.2063	30.0843
0.0131	2.7567	2000	0.2025	35.2159
0.0016	4.1351	3000	0.2244	32.7855

Framework versions

Transformers 4.42.0.dev0
Pytorch 2.3.0+cu121
Datasets 2.19.2
Tokenizers 0.19.1