metadata

library_name: transformers
language:
  - th
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - asr
  - speech-recognition
  - thai
  - custom-model
  - fine-tuning
  - Common Voice
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper Medium TH - Common Voice 17
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_17_0
          type: common_voice_17_0
          config: th
          split: validation[:20%]
          args: th
        metrics:
          - name: Wer
            type: wer
            value: 81.60690571049138

Whisper Medium TH - Common Voice 17

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

Loss: 0.2987
Wer: 81.6069

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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 125
training_steps: 1000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5323	0.6083	250	0.4352	91.2683
0.2568	1.2165	500	0.3432	87.1514
0.2126	1.8248	750	0.3047	83.3333
0.0974	2.4331	1000	0.2987	81.6069

Framework versions

Transformers 4.45.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3