This repository contains Ming-3.0-tts-0.5B, the dense Ming-3.0-tts checkpoint built on Qwen2.5-0.5B. The checkpoint includes the backbone, DiT head, audio tokenizer, speaker encoder and text tokenizer.
Inference requires the Ming-3.0-tts GitHub repository. This Hugging Face repository is for checkpoint distribution and does not provide a standalone inference setup. Clone the GitHub repository and follow its README for the current dependencies, inference code and usage instructions. The CLI scripts and Python APIs referenced below are provided by the GitHub repository.
| Item | Value |
|---|---|
| Architecture | Dense, Qwen2.5-0.5B backbone |
| Parameters | 0.5B |
| Languages | Chinese, English, German, Spanish, French, Korean, Japanese |
| Dialects | Sichuanese, Cantonese |
| Python API | ming_tts.MingTTS |
| CLI | infer.py |
| Sample rate | 44.1 kHz |
git clone https://github.com/inclusionAI/Ming-3.0-tts.git
cd Ming-3.0-tts
pip install -r requirements.txt
Tested on NVIDIA H800-80GB and H20-96G with CUDA 12.4. flash-attn is optional; inference falls back to PyTorch SDPA.
Numbers, dates, units and symbols are normalized with FST grammars. Install pynini, or pass --no_text_normalization to skip text normalization:
conda install -c conda-forge pynini==2.1.6
pip install "huggingface_hub[cli]"
hf download inclusionAI/Ming-3.0-tts-0.5B --local-dir Ming-3.0-tts-0.5b
python infer.py \
--model_path inclusionAI/Ming-3.0-tts-0.5B \
--task TTS \
--language_id Chinese \
--text "傍晚的风从山口吹过来，远处的云慢慢染成了金色。" \
--prompt_wav_path data/wavs/10002287-00000094.wav \
--prompt_text "在此奉劝大家别乱打美白针。" \
--use_spk_emb \
--output output/tts.wav
from ming_tts import MingTTS
model = MingTTS("inclusionAI/Ming-3.0-tts-0.5B")
model.synthesize(
task="TTS",
language_id="Chinese", # English for English text
text="傍晚的风从山口吹过来，远处的云慢慢染成了金色。",
prompt_wav_path="data/wavs/10002287-00000094.wav",
prompt_text="在此奉劝大家别乱打美白针。",
use_spk_emb=True,
output_path="output/tts.wav",
)
Supported tasks are TTS, FREEFORM, VOICE_DESIGN, MULTILINGUAL, BASIC, EMOTION, DIALECT and IP. See the task cookbook for controls and examples.
MULTILINGUAL requires language_id for German, Spanish, French, Korean or Japanese; DIALECT takes no language ID. Freeform uses its own task and cannot be combined with voice design, a built-in voice, emotion, dialect or attribute controls. With a reference clip it follows that voice; without a reference, the instruction can choose the voice.
python tools/preflight.py --model_path /path/to/Ming-3.0-tts-0.5b
Benchmark comparisons from the project README.
Bold and underline mark the best and second-best values among the listed open-source models; ties share a mark. Seed-TTS and NVbench-GT are unranked reference rows.
Evaluated on the German, Spanish, French, Korean, and Japanese subsets of MiniMaxAI/TTS-Multilingual-Test-Set.
Released under the MIT license.