CLI tool for Supertonic MNN inference
Project description
Supertonic MNN CLI
A command-line interface for running Supertonic TTS models using MNN.
Installation
cd supertonic-mnn
uv sync
Usage
# Using local models with default precision (fp16)
uv run supertonic-mnn "Hello world" --voice M1 --output hello.wav --model-dir /path/to/models
# Specify precision
uv run supertonic-mnn "Hello world" --voice M1 --precision fp32
# Download models from HuggingFace (automatic)
uv run supertonic-mnn "Hello world" --voice M1 --precision int8
# Example with py directory (if you have local models in old format)
uv run supertonic-mnn "Hello world" --voice M1 --output hello.wav --model-dir ../py
Available Options
--voice: Voice style (default: M1)--precision: Model precision - fp32, fp16, or int8 (default: fp16)--output: Output audio file path (default: output.wav)--speed: Speech speed multiplier (default: 1.0)--steps: Number of denoising steps (default: 5)--model-dir: Directory containing models (default: ~/.cache/supertonic-mnn)
Features
- MNN Inference: Fast, on-device inference using MNN
- Voice Styles: Supports multiple voice styles (M1, F1, etc.)
- Local Models: Use
--model-dirto specify local model directory
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
supertonic_mnn-0.1.0.tar.gz
(62.8 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file supertonic_mnn-0.1.0.tar.gz.
File metadata
- Download URL: supertonic_mnn-0.1.0.tar.gz
- Upload date:
- Size: 62.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.13 {"installer":{"name":"uv","version":"0.9.13"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f062d09fbd99fb833897bbbabdef0ac979d4b2ccaa5bbe33e03082d9855c69ed
|
|
| MD5 |
095b8f6ce59d58902b98b151d3f2fa45
|
|
| BLAKE2b-256 |
5a4190a81b7122649846438256d364e583505413e22b492c1c15d1e1df062515
|
File details
Details for the file supertonic_mnn-0.1.0-py3-none-any.whl.
File metadata
- Download URL: supertonic_mnn-0.1.0-py3-none-any.whl
- Upload date:
- Size: 9.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.13 {"installer":{"name":"uv","version":"0.9.13"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"22.04","id":"jammy","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
36bcf1d058538de8aab1ed40c8948ab9825604a44dbfb062ac8d225f03c4926f
|
|
| MD5 |
de6994c48799fdaf1385460194b99b9d
|
|
| BLAKE2b-256 |
845307b1e6f6e8476ba2dcda2883dade8cd72f9ea6334f157c76f596ffe6fe8d
|
