🗣️ Whisper Large V3 Turbo Lao Fine-tuned (Laos V10)
Model Overview
This model is a fine-tuned version of OpenAI's Whisper Large V3 Turbo for Lao (ພາສາລາວ) automatic speech recognition (ASR). It has been fine-tuned on the Phonepadith/laos-speech-dataset, a curated dataset containing Lao speech samples and transcriptions.
🧠 Model Details
| Property | Description |
|---|---|
| Base model | openai/whisper-large-v3-turbo |
| Fine-tuned by | @Phonepadith |
| Language | Lao (lo) |
| Task | Automatic Speech Recognition (ASR) |
| Framework | 🤗 Transformers, PyTorch |
| Dataset | Phonepadith/laos-speech-dataset |
| Sampling rate | 16 kHz |
| License | MIT (same as base model unless otherwise stated) |
📊 Training Details
- Fine-tuned on: Lao speech dataset 100 hours
- Input: 16kHz mono audio
- Output: Lao text transcription
- Epochs: 13
- Batch size: 2
- Learning rate: 1e-5
- Optimizer: AdamW
- Evaluation metric: Word Error Rate (WER)
🚀 Usage Example
from transformers import WhisperProcessor, WhisperForConditionalGeneration
import torch
import torchaudio
# Load model and processor
model_id = "Phonepadith/whisper-3-large-turbo-lao-finetuned-v10"
processor = WhisperProcessor.from_pretrained(model_id)
model = WhisperForConditionalGeneration.from_pretrained(model_id)
# Load an audio file (16kHz mono)
speech_array, sampling_rate = torchaudio.load("example.wav")
speech_array = torchaudio.functional.resample(speech_array, sampling_rate, 16000)
# Preprocess and generate transcription
input_features = processor(
speech_array.squeeze().numpy(),
sampling_rate=16000,
return_tensors="pt"
).input_features
predicted_ids = model.generate(input_features)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
print("Transcription:", transcription)
📈 Evaluation Results
Training Metrics
TrainOutput(global_step=45000, training_loss=0.03216575982156727, metrics={'train_runtime': 57148.3905, 'train_samples_per_second': 6.299, 'train_steps_per_second': 0.787, 'total_flos': 6.137824149504e+20, 'train_loss': 0.03216575982156727, 'epoch': 12.49305941143809})
🧩 Intended Use
This model is designed for speech-to-text transcription in Lao, such as:
- Voice command systems
- Lao language learning apps
- Accessibility tools (subtitles, transcripts)
- Cultural and linguistic research
⚠️ Limitations
- May struggle with code-switching (mix of Lao and English)
- Background noise or strong dialectal accents may reduce accuracy
- Whisper's built-in tokenizer may occasionally normalize Lao text (tone marks or spacing)
🪪 Citation
If you use this model in your research, please cite:
@misc{phonepadith2025whisperlaoturbo,
title = {Whisper Large V3 Turbo Fine-tuned for Lao ASR},
author = {Phonepadith Phoummavong},
year = {2025},
howpublished = {\url{https://huggingface.co/Phonepadith/whisper-3-large-turbo-lao-finetuned-v10}},
}
💬 Contact
For questions, collaboration, or dataset contributions:
- 📧 Email: phonepadithpp@gmail.com
- 🤗 Hugging Face Profile
Note: This model is part of ongoing efforts to improve ASR capabilities for low-resource languages like Lao. Contributions and feedback are welcome!