Features
Thai language speech recognition
Fine-tuned Whisper for Thai phonetics
Free Hugging Face Space demo
Open-source model weights download
No-code interface for audio upload
Supports common audio formats via browser
Short audio transcription (demo limit)
Community-contributed model on Hugging Face
Based on OpenAI Whisper architecture
Designed for Thai tonal accuracy
Transfer learning from multilingual Whisper
Suitable for ASR research and benchmarking
Multilingual speech transcription (99+ languages)
To-English speech translation
Zero-shot robustness to accents, noise, technical language
Open-source models and inference code
Encoder-decoder Transformer architecture
Trained on 680,000 hours of diverse data
Log-Mel spectrogram input
30-second audio chunk processing
Multiple model sizes (tiny to large)
Whisper.cpp for CPU inference
Fine-tuning via Hugging Face integration
Turbo model on OpenAI API
OpenAI API at $0.006 per minute
