liyunlongaaa/MiMo-Tokenizer-Trainer

Unofficial implementation of training pipeline in mimo-tokenizer about "MiMo-Audio: Audio Language Models are Few-Shot Learners"

stars

commits

Python

primary language

Nov 9, 2025

updated

README

MiMo-Tokenizer-Trainer

requirement

pip install requirements.txt

stage1

accelerate launch --config_file config/acclerate/accelerate_config_zero2.yaml trainer/trainer_stage1.py -c config/stage1.json

stage2

accelerate launch --config_file config/acclerate/accelerate_config_zero2.yaml trainer/trainer_stage2.py -c config/stage2.json

more details please check code, just an example for personal experiment.

Contributors

liyunlongaaa

2 commits

Similar repos

anakib1/MangoRAG

ZhangXInFD/SpeechTokenizer

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer…

664

slp-rl/slamkit

SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming:…

228

XiaomiMiMo/MiMo-Audio-Tokenizer

Model

frothywater/kanade-tokenizer

Kanade is a single-layer disentangled speech tokenizer that extracts compact tokens suitable for…

115

Respaired/Higgs_Codec_Extended

zhvng/open-musiclm

Implementation of MusicLM, a text to music model published by Google Research, with a few…

559

XiaomiMiMo/MiMo-Audio

MiMo-Audio: Audio Language Models are Few-Shot Learners

1,080

Languages

Python

100.0%

liyunlongaaa/MiMo-Tokenizer-Trainer

Unofficial implementation of training pipeline in mimo-tokenizer about "MiMo-Audio: Audio Language Models are Few-Shot Learners"

stars

commits

Python

primary language

Nov 9, 2025

updated

README

MiMo-Tokenizer-Trainer

requirement

pip install requirements.txt

stage1

accelerate launch --config_file config/acclerate/accelerate_config_zero2.yaml trainer/trainer_stage1.py -c config/stage1.json

stage2

accelerate launch --config_file config/acclerate/accelerate_config_zero2.yaml trainer/trainer_stage2.py -c config/stage2.json

more details please check code, just an example for personal experiment.

Similar repos

anakib1/MangoRAG

ZhangXInFD/SpeechTokenizer

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer…

664

slp-rl/slamkit

SlamKit is an open source tool kit for efficient training of SpeechLMs. It was used for "Slamming:…

228

XiaomiMiMo/MiMo-Audio-Tokenizer

Model

frothywater/kanade-tokenizer

Kanade is a single-layer disentangled speech tokenizer that extracts compact tokens suitable for…

115

Respaired/Higgs_Codec_Extended

zhvng/open-musiclm

Implementation of MusicLM, a text to music model published by Google Research, with a few…

559

XiaomiMiMo/MiMo-Audio

MiMo-Audio: Audio Language Models are Few-Shot Learners

1,080

Contributors

liyunlongaaa

2 commits

Languages

Python

100.0%