Skip to content
Other

MaprangSTT

компактный Thai ASR для диалектов

1 min read

MaprangSTT — модель распознавания тайской речи на базе Cactus-Compute/whistle от PyThaiNLP. Поддерживает стандартный тайский и региональные диалекты: центральный, исанский, северный, корат, южный, а также речь пожилых людей. Обучена на открытых данных, итоговый архив .cact занимает 32,49 МБ.

Ключевые особенности

  • Обучение на 1 022,78 часа (594 231 клип) тайской речи.
  • Quantization-aware LoRA: rank=16, alpha=32, 15 групп весов.
  • Формат W4A8: 4-битные веса, 8-битные активации и KV cache.
  • Расширенный Thai SentencePiece словарь: +2 067 токенов.
  • Готовый .cact на 32,49 МБ для инференса на CPU, GPU и мобильных устройствах.

Пример

from huggingface_hub import hf_hub_download
from needle import Whistle

model = Whistle(hf_hub_download("pythainlp/MaprangSTT", "maprang.cact"))
print(model.transcribe("speech.wav", language="th")["text"])
ПодробнееНа Google FLEURS (th_th): CER 13,58%, WER 31,05%.
Для сравнения, openai/whisper-small при 967 МБ даёт CER 24,21% и WER 75,74%.
Вход — 16 кГц моно PCM .wav; обучение шло на RTX 4090 24 ГБ.
Есть LoRA-адаптер 29,0 МБ и сборка .cact с 4 или 6 слоями декодера.
Discuss Telegram 1

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # pythainlp/MaprangSTT
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download pythainlp/MaprangSTT --local-dir ~/models/MaprangSTT
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to MaprangSTT
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of whistle (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 5All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 2All on Hugging Face

About the model

pythainlp/MaprangSTT
Author
pythainlp
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

01

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments

Other

d3-edge

d3-edge