README.md

metadata

base_model: openai/whisper-large-v3
datasets:
  - mozilla-foundation/common_voice_11_0
language:
  - th
library_name: peft
license: apache-2.0
metrics:
  - wer
  - ter
  - chrf
  - cer
  - bleu
  - suber
tags:
  - generated_from_trainer
model-index:
  - name: Whisper Large V3 Thai Lora - Magi Boss
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: th
          split: None
          args: 'config: th, split: validation'
        metrics:
          - type: wer
            value: 0.8101
            name: Wer
          - name: Ter
            type: ter
            value: 81.0089
          - name: ChrF
            type: chrf
            value: 87.4811
          - name: CER
            type: cer
            value: 0.1041
          - type: bleu
            value: 8.7391
            name: Bleu
          - name: SubER
            type: suber
            value: 0.8189
pipeline_tag: automatic-speech-recognition

Whisper Large V3 Thai Lora - Magi Boss

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset (Training Set 20000 row, Validation Set 500 row). It achieves the following results on the evaluation set:

• Loss: 0.1894
• WER: 0.8101
• TER: 81.0089
• ChrF: 87.4811
• CER: 0.1041
• BLEU: 8.7391
• SubER: 0.8189

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 25
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Ter	Chrf	Cer	Bleu	SubER
0.3053	0.32	50	0.2052	0.8457	84.5697	86.6971	0.1115	7.8703	0.8640
0.3752	0.64	100	0.1937	0.8323	83.2344	86.9801	0.1087	8.1510	0.8469
0.2794	0.96	150	0.1894	0.8101	81.0089	87.4811	0.1041	8.7391	0.8189

Framework versions

• PEFT 0.12.1.dev0
• Transformers 4.45.0.dev0
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1