Model reference · open weights

monsoon-whisper-medium-gigaspeech2

Available as managed deployment Audio typhoon-ai Speech→text 1 variants 1k dl/mo

monsoon-whisper-medium-gigaspeech2 is an open-weight audio or speech model from typhoon-ai. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bytyphoon-ai
TypeAudio & music
TaskSpeech→text
Parameters (lead)764M
Runs withtransformers
Released2024-07-12
Popularity1k downloads / month
LicenceOpen weights

About

What monsoon-whisper-medium-gigaspeech2 is

Monsoon-Whisper-Medium-GigaSpeech2 is a 🇹🇭 Thai Automatic Speech Recognition (ASR) model. It is based on Whisper-Medium and fine-tuned on GigaSpeech2.

Originally developed as a scale experiment for research on emergent capabilities in ASR tasks. It performs well in the wild, including with audio sourced from YouTube and in noisy environments.

More details can be found in our Typhoon-Audio Release Blog.

By using this model, you agree to the OpenTyphoon Terms and Conditions and acknowledge the Privacy Notice: https://opentyphoon.ai/tac · https://opentyphoon.ai/privacy

Read the full model card

Model Description

  • Model type: Whisper Medium.
  • Requirement: transformers 4.38.0 or newer.
  • Primary Language(s): Thai 🇹🇭
  • License: Apache 2.0

Usage Example

from transformers import WhisperProcessor, WhisperForConditionalGeneration
import torchaudio
import torch

model_path = "scb10x/monsoon-whisper-medium-gigaspeech2"
device = "cuda"
filepath = 'audio.wav'

processor = WhisperProcessor.from_pretrained(model_path)
model = WhisperForConditionalGeneration.from_pretrained(
    model_path, torch_dtype=torch.bfloat16
)
model.to(device)
model.eval()

model.config.forced_decoder_ids = processor.get_decoder_prompt_ids(
    language="th", task="transcribe"
)
array, sr = torchaudio.load(filepath)
input_features = (
    processor(array, sampling_rate=sr, return_tensors="pt")
    .to(device)
    .to(torch.bfloat16)
    .input_features
)
predicted_ids = model.generate(input_features)
transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
print(transcription)

Evaluation Results

ModelWER (GS2)WER (CV17)CER (GS2)CER (CV17)
whisper-large-v337.0222.6324.038.49
whisper-medium55.6443.0137.5516.41
biodatlab-whisper-th-medium-combined31.0014.2521.205.69
biodatlab-whisper-th-large-v3-combined29.0215.7219.966.32
monsoon-whisper-medium-gigaspeech222.7420.7914.156.92

Intended Uses & Limitations

This model is experimental and may not always be accurate. Developers should carefully assess potential risks in the context of their specific applications.

Follow us & Support

  • https://twitter.com/opentyphoon
  • https://discord.gg/us5gAYmrxw

Typhoon Team

Kunat Pipatanakul, Potsawee Manakul, Sittipong Sripaisarnmongkol, Natapong Nitarach, Warit Sirichotedumrong, Adisai Na-Thalang, Phatrasek Jirabovonvisut, Parinthapat Pengpun, Krisanapong Jirayoot, Pathomporn Chokchainant, Kasima Tharnpipitchai

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys monsoon-whisper-medium-gigaspeech2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (monsoon-whisper-medium-gigaspeech2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="monsoon-whisper-medium-gigaspeech2" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms