inclusionAI/Ming-3.0-tts-0.5B

Name: inclusionAI/Ming-3.0-tts-0.5B
Creator: inclusionAI
License: mit

text-to-speechtransformersVerified checksumsaudiotext-to-speechvoice-cloningmultilingualspeech-generationtransformers

License: mit
Size: 2.8 GB
Revision: main
Downloads in the last 30 days: 0 / 30 days

Mirrored from inclusionAI/Ming-3.0-tts-0.5B

All models by inclusionAI →

Ming-3.0-tts-0.5B

Dense 0.5B multilingual speech synthesis with paralinguistic and free-form control.

GitHub |

Blog & Demos |

ModelScope

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.

Model Details

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

Capabilities

Zero-shot voice cloning from a short reference clip
Voice Design from a natural-language speaker description
Free-form control of delivery and speaking style
Built-in Chinese and English voices
14 inline tags for breath, cough, sigh, laughter, hesitation, surprise and question/confirmation sounds in Chinese or English
Explicit emotion, speed, pitch and volume control
Multilingual synthesis and Sichuanese/Cantonese dialect control

Recommended built-in voices: UK_George, US_Emma, 灵小柔 and 灵楷. See the voice catalog for the full list and voice descriptions. Use the exact ip values shown.

Quick Start

Installation

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:

Download

CLI Inference

bash

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

Python API

python

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.

Verify the Checkpoint

Performance

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.

Zero-shot TTS (Seed-TTS testset)

Model	seed-tts-eval-zh		seed-tts-eval-en
Model	WER ↓	SIM ↑	WER ↓	SIM ↑
Seed-TTS	1.110%	0.796	2.240%	0.762
GLM-TTS	1.030%	0.761	2.230%	0.672
Qwen3-TTS	1.070%	—	1.390%	—
Qwen3-TTS-12Hz-0.6B-Base	0.920%	—	1.320%	—
Qwen3-TTS-12Hz-1.7B-Base	0.770%	—	1.240%	—
CosyVoice3-0.5B	1.160%	0.780	2.020%	0.718
CosyVoice3-1.5B	0.710%	0.775	1.450%	0.695
F5-TTS	1.560%	0.741	1.830%	0.647
Ming-3.0-tts-0.5b	0.800%	0.758	1.584%	0.691
Ming-3.0-tts-tiny	0.820%	0.781	1.666%	0.728

Multilingual (MiniMax test set, selected languages)

Evaluated on the German, Spanish, French, Korean, and Japanese subsets of MiniMaxAI/TTS-Multilingual-Test-Set.

Model	German		Spanish		French		Korean		Japanese
Model	WER ↓	SIM ↑	WER ↓	SIM ↑	WER ↓	SIM ↑	CER ↓	SIM ↑	CER ↓	SIM ↑
dots.tts	0.452%	0.798	2.593%	0.839	19.878%	0.789	4.837%	0.853	5.134%	0.838
VoxCPM2	0.963%	0.790	1.324%	0.836	3.380%	0.761	3.547%	0.839	4.358%	0.825
Fish Audio S2	1.045%	0.714	1.216%	0.748	3.636%	0.698	1.675%	0.761	3.427%	0.755
FireRedTTS3	0.348%	0.825	1.086%	0.868	4.366%	0.807	1.644%	0.864	3.418%	0.825
Ming-3.0-tts-0.5b	0.365%	0.753	1.099%	0.763	4.264%	0.675	1.728%	0.793	3.765%	0.765
Ming-3.0-tts-tiny	0.325%	0.791	0.971%	0.797	3.470%	0.733	6.000%	0.797	3.427%	0.780

Each open-source model was evaluated using its recommended inference settings under a unified ASR-based WER/CER evaluation protocol.

Paralinguistic Control (NVBench)

Model	Single						Multi
	Chinese			English			Chinese			English
	CER	PCER	OCER	CER	PCER	OCER	CER	PCER	OCER	CER	PCER	OCER
NVbench-GT	3.86	9.38	4.07	6.73	8.31	6.90	3.79	23.71	5.07	7.26	21.41	8.62
Orpheus-TTS	11.36	88.77	13.91	9.03	71.92	10.63	19.83	84.85	24.38	8.68	71.46	11.89
SMIIP-NV-CV2	8.80	75.64	11.34	17.92	56.80	19.47	10.66	77.20	14.79	20.93	54.49	23.87
Emilia-NV-CV2	5.05	40.00	6.64	12.50	55.30	13.21	5.54	48.74	8.09	11.71	60.28	14.63
CosyVoice3	3.85	57.69	5.86	7.87	62.75	9.06	4.75	61.94	8.26	6.39	57.84	10.69
NV-FlexiVoice	6.98	31.08	8.15	11.88	50.43	13.21	8.20	39.37	10.39	9.60	51.32	13.76
NV-CV3	3.80	27.69	4.90	8.33	46.13	9.44	3.44	30.04	4.84	6.70	47.13	10.10
Ming-3.0-tts-0.5b	2.70	22.80	3.20	7.60	37.00	8.90	3.50	36.60	8.10	7.90	47.30	10.40
Ming-3.0-tts-tiny	2.80	17.23	3.20	5.86	32.95	7.05	4.49	32.88	5.81	5.12	46.13	7.68

Dialect Control

Model	WSC-Eval-TTS-easy			WSC-Eval-TTS-hard			WSYue-TTS-eval-Base			WSYue-TTS-eval-Coverage
Model	CER ↓	SIM ↑	ACC ↑	CER ↓	SIM ↑	ACC ↑	CER ↓	SIM ↑	ACC ↑	CER ↓	SIM ↑	ACC ↑
Qwen3-TTS	4.13%	—	—	7.35%	—	—	—	—	—	—	—	—
CosyVoice3-0.5B	3.17%	0.696	76.05%	4.07%	0.723	81.41%	8.36%	0.611	91.70%	8.95%	0.658	95.80%
CosyVoice3-1.5B + DiffRO-EMO	7.14%	0.703	—	9.06%	0.601	—	14.38%	0.812	—	13.74%	0.826	—
CosyVoice2-WSC	4.28%	0.728	—	8.87%	0.626	—	—	—	—	—	—	—
CosyVoice2-WSC-SFT	4.08%	0.788	—	7.22%	0.680	—	—	—	—	—	—	—
CosyVoice2-Yue	—	—	—	—	—	—	10.33%	0.821	—	9.49%	0.834	—
Sparks-TTS	10.83%	0.677	—	12.52%	0.545	—	27.79%	0.762	—	24.25%	0.781	—
Ming-3.0-tts-0.5b	2.27%	0.689	80.68%	3.35%	0.691	87.64%	6.15%	0.586	98.00%	8.15%	0.622	95.27%
Ming-3.0-tts-tiny	2.53%	0.721	86.09%	3.11%	0.738	88.94%	7.40%	0.605	92.90%	8.67%	0.653	95.16%

Emotion Control (CV3)

Model	Average	Text-Related			Text-Unrelated
Model	Average	Happy	Sad	Angry	Happy	Sad	Angry
CosyVoice3-0.5B	66.33%	92%	70%	72%	64%	42%	58%
CosyVoice3-1.5B	63.00%	86%	64%	72%	64%	44%	48%
CosyVoice3-1.5B + DiffRO-EMO	77.67%	98%	68%	84%	98%	50%	68%
F5-TTS	64.67%	92%	52%	72%	80%	28%	64%
Sparks-TTS	55.33%	80%	56%	50%	50%	60%	36%
Ming-3.0-tts-0.5b	72.33%	96%	76%	94%	52%	36%	80%
Ming-3.0-tts-tiny	74.00%	98%	82%	90%	60%	36%	78%

Emotion Control (CV3N, hard emotion control)

Voice Design (InstructTTSEval-ZH)

Model	Average	APS	DSD	RP
Qwen3-TTS	77.13%	85.20%	81.10%	65.10%
Mimo-Audio-7B-Instruct	70.50%	75.70%	74.30%	61.50%
VoiceSculptor	67.30%	75.70%	64.70%	61.50%
VoxInstruct	47.47%	47.50%	52.30%	42.60%
Ming-3.0-tts-0.5b	72.29%	78.54%	77.28%	61.06%
Ming-3.0-tts-tiny	75.37%	85.10%	79.90%	61.10%

Basic Attribute Control

Limitations

Speaker similarity is weaker than content accuracy; French SIM is the clearest multilingual gap.
NVBench Multi trails Single; stability with several paralinguistic events in one sentence is still improving.
Emotion control is harder when the words carry no emotional signal.
Pitch is less accurate than speed and volume, and open-ended Voice Design does not yet match the strongest evaluated system.

Usage Disclaimer

Voice cloning and built-in character voices are provided for research and legitimate creative use. Do not use them to impersonate a real person without consent, to deceive, or for any illegal purpose.
Label synthetic speech as synthetic where it could be mistaken for a real recording.
The authors accept no liability for misuse. If you find abuse of this project, please report it to us.

Acknowledgements

Qwen2.5 for the backbone
CAM++ for speaker embedding extraction
Ming-omni-tts, the previous generation, whose audio tokenizer this release builds on

License

Released under the MIT license.

Model	Speed	Volume	Pitch	Average	WER ↓	SIM ↑
CosyVoice3-0.5B	100.00%	97.67%	65.33%	87.67%	1.210%	0.580
Ming-3.0-tts-0.5b	99.00%	95.00%	86.00%	93.30%	0.317%	0.712
Ming-3.0-tts-tiny	93.00%	93.00%	78.70%	88.23%	0.274%	0.742

Model	Speed	Volume	Pitch	Average	WER ↓	SIM ↑
CosyVoice3-0.5B	100.00%	97.67%	65.33%	87.67%	1.210%	0.580
Ming-3.0-tts-0.5b	99.00%	95.00%	86.00%	93.30%	0.317%	0.712
Ming-3.0-tts-tiny	93.00%	93.00%	78.70%	88.23%	0.274%	0.742