Downloads · 30 days
11
20% of all-time downloads
KittipatPaisanpudinun/Whisper_Finetune_ThaiFood-Ordering
Whisper_Finetune_ThaiFood-Ordering is a automatic speech recognition model from KittipatPaisanpudinun. Use it when you need speech turned into text. It is set up for ctranslate2. The card lists the license as mit.
[](https://opensource.org/licenses/MIT) [](https://huggingface.co/openai/whisper-large-v3-turbo) [](https://github.com/SYSTRAN/faster-whisper)
Downloads · 30 days
11
20% of all-time downloads
All-time downloads
55
Public
Repo size
1.6 GB
Likes
0
Public
Click a slice to open those files.
.bin1.6 GB · 100%
From the Hugging Face model README
A domain-adapted Thai Automatic Speech Recognition (ASR) model fine-tuned specifically for Thai restaurant, food court, and beverage ordering contexts. Built upon OpenAI Whisper Large-v3-Turbo, this model has been optimized and converted into CTranslate2 (faster-whisper) format for ultra-fast, real-time inference on both GPU (CUDA) and CPU environments.
faster-whisper, reducing VRAM consumption by up to 50% while accelerating transcription speed with float16 and int8_float16 quantizations.The model was evaluated against a dedicated Thai food ordering test benchmark (500 samples), comparing the fine-tuned model directly with the pre-trained baseline model (openai/whisper-large-v3-turbo):
| Model | Character Error Rate (CER) ↓ | Accuracy (%) ↑ | Real-Time Factor (RTF) ↓ |
|---|---|---|---|
| OpenAI Whisper Large-v3-Turbo (Pre-trained Baseline) | 18.8% (0.188) | 81.2% | 0.058 |
| Whisper-Turbo (Baseline Fine-tuned) | 1.6% (0.016) | 98.4% | 0.138 |
| Whisper_Finetune_ThaiFood-Ordering (Ours) | 1.3% (0.013) | 98.7% | 0.051 |
Definitions:
- CER (Character Error Rate): Lower is better. Measures character-level transcription discrepancies for Thai script.
- Accuracy: Calculated as $1 - \text{CER}$.
- RTF (Real-Time Factor): Lower is better. Processing execution time divided by the audio duration.
openai/whisper-large-v3-turbo (32 Encoder layers, 4 Decoder layers, 128 Mel frequency bins)faster-whisperThis model is formatted in CTranslate2, allowing direct inference with the lightweight and highly optimized faster-whisper library.
pip install faster-whisper
from faster_whisper import WhisperModel
# Load model directly from Hugging Face Hub or local path
model_id = "KittipatPaisanpudinun/Whisper_Finetune_ThaiFood-Ordering"
# Initialize model with float16 or int8_float16 on GPU
model = WhisperModel(model_id, device="cuda", compute_type="float16")
# Transcribe Thai ordering audio
segments, info = model.transcribe(
"order_sample.wav",
language="th",
vad_filter=True, # Filter out non-speech silence
beam_size=5,
initial_prompt="สั่งอาหาร เมนู ข้าวมันไก่ กะเพราหมูกรอบ หวานน้อย เผ็ดกลาง"
)
print(f"Detected language: '{info.language}' with probability {info.language_probability:.2f}")
full_text = ""
for segment in segments:
print(f"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}")
full_text += segment.text + " "
print("\nResult:", full_text.strip())
from faster_whisper import WhisperModel
model_id = "KittipatPaisanpudinun/Whisper_Finetune_ThaiFood-Ordering"
# Initialize on CPU using int8 quantization to save memory
model = WhisperModel(model_id, device="cpu", compute_type="int8")
segments, _ = model.transcribe("order_sample.mp3", language="th")
for segment in segments:
print(segment.text)
vad_filter=True in model.transcribe() is recommended to avoid false positive triggers.If you use this model or dataset in your research or application, please cite:
@article{kittipat2026whisperthaifood,
title={Comparative Study and Fine-tuning of Whisper AI Models for Thai Speech Recognition in Food Ordering Contexts},
author={Kittipat Paisanpudinun},
year={2026},
publisher={Hugging Face},
howpublished={\url{https://huggingface.co/KittipatPaisanpudinun/Whisper_Finetune_ThaiFood-Ordering}}
}
License: MIT License
Developed by: Kittipat Paisanpudinun