No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from inclusionAI/Ming-3.0-tts-tiny
All models by inclusionAI →
7.9B-A1.3B multilingual MoE speech synthesis with paralinguistic and free-form control.
GitHub |
Blog & Demos |
ModelScope
This repository contains Ming-3.0-tts-tiny, the Ming-3.0-tts mixture-of-experts checkpoint built on Ling V3. Its Ling V3 backbone has 7.9B total parameters and activates about 1.3B parameters per token. The repository includes sharded weights, supporting model code, 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.
podcast)
Tiny uses a separate reference inference environment: Python 3.10.15, PyTorch and torchaudio 2.7.1+cu118 (CUDA 11.8 wheels), and transformers==4.46.3. Install the pinned dependencies from requirements-tiny.txt in a dedicated environment, as other dependency versions differ from 0.5B. We recommend using NVIDIA H800 for inference.
Loading configures the release runtime (bf16, portable MoE loop, fp32 recurrent state) and checks the checkpoint against it; generate() defaults to cfg_scale=2.0, temperature=0, flow_steps=10, and sigma=0.25.
Each call selects one task and accepts the inputs listed below:
Freeform always requires a reference clip and cannot be combined with voice design, a built-in voice, emotion, dialect or attribute controls. For podcast, start every dialogue line with speaker_N: and provide one reference audio clip and transcript per speaker, in speaker order. Repeat --prompt_wav and --prompt_text on the command line.
See the Tiny examples for a Podcast Python example and examples/one_click/ for scripts for every task. python infer_tiny.py --help lists the CLI arguments.
For installation, follow the vLLM-Omni official installation guide; vLLM-Omni serves this checkpoint through the OpenAI-compatible /v1/audio/speech endpoint. The current recipe targets vLLM 0.32.0. Use a separate environment from the reference inference setup above.
Start the server in one terminal:
The HF model ID selects the two-stage Ming3-TTS pipeline automatically and downloads the weights and required assets on first launch. Both stages share GPU 0. A complete local model directory may also be used; pass --revision <HF-commit> to pin a remote checkpoint.
After the server is ready, run this reference-free voice design example in another terminal:
The output is a mono 44.1 kHz WAV. Voice cloning uses ref_audio and its matching transcript in ref_text; speech controls use instructions. For voice cloning, dialect and emotion controls, built-in voices, multi-speaker Podcast, and PCM streaming, see the upstream Ming-3.0-TTS recipe.
SGLang-Omni serves this checkpoint on one GPU:
Synthesize speech through the OpenAI-compatible endpoint:
response_format accepts wav, mp3, flac, and pcm. For zero-shot voice cloning, pass ref_audio (a server-side path or a data: URL) together with ref_text, the transcript of the reference recording. See the SGLang-Omni cookbook for details.
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.
Each open-source model was evaluated using its recommended inference settings under a unified ASR-based WER/CER evaluation protocol.
Released under the MIT license.
git clone https://github.com/inclusionAI/Ming-3.0-tts.gitcd Ming-3.0-ttsconda create -n ming-tiny python=3.10.15 -yconda activate ming-tinypip install -r requirements-tiny.txtpip install "huggingface_hub[cli]"hf download inclusionAI/Ming-3.0-tts-tiny --local-dir Ming-3.0-tts-tinypython infer_tiny.py \ --model_path inclusionAI/Ming-3.0-tts-tiny \ --task dialect \ --text "今日天气几好，我哋食完饭一齐去海边行下啦。" \ --dialect 广粤话 \ --prompt_wav data/wavs/10002287-00000094.wav \ --output_path output/tiny.wavfrom ming_tiny import MingTinyTTS
tts = MingTinyTTS.from_pretrained("inclusionAI/Ming-3.0-tts-tiny", device="cuda:0")tts.generate( task="seed", text="傍晚的风从山口吹过来，远处的云慢慢染成了金色。", prompt_wav="data/wavs/10002287-00000094.wav", prompt_text="在此奉劝大家别乱打美白针。", target_language="Chinese", # English for English text output_path="outputs/seed.wav",)python tools/preflight_tiny.py --model_path /path/to/Ming-3.0-tts-tinyvllm serve inclusionAI/Ming-3.0-tts-tiny --omni --port 8000curl --fail-with-body --silent --show-error http://127.0.0.1:8000/v1/audio/speech \ -H 'Content-Type: application/json' \ -d '{ "model": "inclusionAI/Ming-3.0-tts-tiny", "input": "傍晚的风从山口吹过来，远处的云慢慢染成了金色。", "instructions": "{\"风格\":\"年轻女声，声音清晰自然。\"}", "response_format": "wav", "extra_params": {"temperature": 0.0, "ming3_cfg": 1.0}, "seed": 1234 }' --output ming3_tiny_design.wavsgl-omni serve --model-path inclusionAI/Ming-3.0-tts-tinycurl -X POST http://127.0.0.1:8000/v1/audio/speech \ -H "Content-Type: application/json" \ -d '{ "model": "inclusionAI/Ming-3.0-tts-tiny", "input": "Get the trust fund to the bank early.", "response_format": "wav", "seed": 123 }' \ --output speech.wav