chuuhtetnaing/whisper-medium-myanmar

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

whisper-medium-myanmar

This model is a fine-tuned version of openai/whisper-medium on the chuuhtetnaing/myanmar-speech-dataset-openslr-80 dataset. It achieves the following results on the evaluation set:

• —Loss: 0.2282
• —Wer: 49.4657

Usage

from datasets import Audio, load_dataset
from transformers import pipeline

# Load a sample audio
dataset = load_dataset("chuuhtetnaing/myanmar-speech-dataset-openslr-80")
dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
test_dataset = dataset['test']
input_speech = test_dataset[42]['audio']

pipe = pipeline(model='chuuhtetnaing/whisper-medium-myanmar')

output = pipe(input_speech, generate_kwargs={"language": "myanmar", "task": "transcribe"})
print(output['text']) # ကျမ ပြည်ပ မှာ ပညာသင် တော့ စာမေးပွဲ ကို တပတ်တခါ စစ်တယ်

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 0.0003
• —trainbatchsize: 40
• —evalbatchsize: 40
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 200
• —num_epochs: 50
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.35.2
• —Pytorch 2.1.1+cu121
• —Datasets 2.14.5
• —Tokenizers 0.15.1