metadata
language: th
license: apache-2.0
tags:
- whisper
- thai
- asr
- speech-recognition
- lora
- peft
- lotusdis
datasets:
- custom
base_model: nectec/Pathumma-whisper-th-large-v3
pipeline_tag: automatic-speech-recognition
🇹🇠Whisper Thai - LOTUSDIS Fine-tuned (LoRA)
Fine-tuned nectec/Pathumma-whisper-th-large-v3 for Thai distant meeting transcription.
Training Details
- Task: LOTUSDIS Distant Meeting Transcription Challenge
- Method: LoRA (rank=64, alpha=128)
- Training data: Multi-microphone (6 mic types) ≈ 95K samples
- Epochs: 1
- Effective batch size: 48
- Precision: BF16
- Trainable params: ~2.4% of total
Usage
from transformers import pipeline
asr = pipeline(
"automatic-speech-recognition",
model="Kanompung/whisper-th-lotusdis-lora",
device="cuda",
chunk_length_s=30,
)
result = asr("audio.mp3", generate_kwargs={"language": "thai", "task": "transcribe"})
print(result["text"])
LoRA Adapter Only
If you want just the adapter (~150 MB):
from peft import PeftModel
from transformers import WhisperForConditionalGeneration
base = WhisperForConditionalGeneration.from_pretrained("nectec/Pathumma-whisper-th-large-v3")
model = PeftModel.from_pretrained(base, "Kanompung/whisper-th-lotusdis-lora-adapter")