commit 3e9415df12633f8a74ac6f92418c7cd5c8c4bf0e Author: Jiameng Gao <19616679+jiamenguk@users.noreply.github.com> Date: Thu Oct 2 13:49:54 2025 +0100 open-source commit diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..9d576c2 --- /dev/null +++ b/.gitignore @@ -0,0 +1,213 @@ +# MacOS +**.DS_Store + +# Emacs +*~ + +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[codz] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py.cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# UV +# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +#uv.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +#poetry.lock +#poetry.toml + +# pdm +# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. +# pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python. +# https://pdm-project.org/en/latest/usage/project/#working-with-version-control +#pdm.lock +#pdm.toml +.pdm-python +.pdm-build/ + +# pixi +# Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control. +#pixi.lock +# Pixi creates a virtual environment in the .pixi directory, just like venv module creates one +# in the .venv directory. It is recommended not to include this directory in version control. +.pixi + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.envrc +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintained in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +#.idea/ + +# Abstra +# Abstra is an AI-powered process automation framework. +# Ignore directories containing user credentials, local state, and settings. +# Learn more at https://abstra.io/docs +.abstra/ + +# Visual Studio Code +# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore +# that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore +# and can be added to the global gitignore or merged into this file. However, if you prefer, +# you could uncomment the following to ignore the entire vscode folder +# .vscode/ + +# Ruff stuff: +.ruff_cache/ + +# PyPI configuration file +.pypirc + +# Cursor +# Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to +# exclude from AI features like autocomplete and code analysis. Recommended for sensitive data +# refer to https://docs.cursor.com/context/ignore-files +.cursorignore +.cursorindexingignore + +# Marimo +marimo/_static/ +marimo/_lsp/ +__marimo__/ diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml new file mode 100644 index 0000000..bada574 --- /dev/null +++ b/.pre-commit-config.yaml @@ -0,0 +1,22 @@ +repos: + - repo: https://github.com/pre-commit/pre-commit-hooks + rev: v4.5.0 # Use the latest tag from the repo + hooks: + - id: trailing-whitespace + - id: end-of-file-fixer + - id: check-yaml + - id: check-added-large-files + - id: requirements-txt-fixer + + - repo: https://github.com/psf/black + rev: 24.4.2 # Use the appropriate version of black + hooks: + - id: black + language_version: python3 + args: [--line-length=100] + + - repo: https://github.com/PyCQA/flake8 + rev: 7.0.0 + hooks: + - id: flake8 + args: [--max-line-length=100] diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..261eeb9 --- /dev/null +++ b/LICENSE @@ -0,0 +1,201 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright [yyyy] [name of copyright owner] + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. diff --git a/README.md b/README.md new file mode 100644 index 0000000..be48c4f --- /dev/null +++ b/README.md @@ -0,0 +1,194 @@ +# NeuTTS Air + +||VIDEO|| + +*Click the image above to watch NeuTTS Air in action on YouTube!* + +*Created by [Neuphonic](http://neuphonic.com/) - building faster, smaller, on-device voice AI* + +State-of-the-art Voice AI has been locked behind web APIs for too long. NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. + +## Key Features + +- 🗣Best-in-class realism for its size - produces natural, ultra-realistic voices that sound human +- 📱Optimised for on-device deployment - provided in GGML format, ready to run on phones, laptops, or even Raspberry Pis +- 👫Instant voice cloning - create your own speaker with as little as 3 seconds of audio +- 🚄Simple LM + codec architecture built off a 0.5B backbone - the sweet spot between speed, size, and quality for real-world applications + +## Model Details + +NeuTTS Air is built off Qwen 0.5B - a lightweight yet capable language model optimised for text understanding and generation - as well as a powerful combination of technologies designed for efficiency and quality: + +- **Audio Codec**: [NeuCodec](https://huggingface.co/neuphonic/neucodec) - our proprietary neural audio codec that achieves exceptional audio quality at low bitrates using a single codebook +- **Format**: Available in GGML format for efficient on-device inference +- **Responsibility**: Watermarked outputs +- **Inference Speed**: Real-time generation on mid-range devices +- **Power Consumption**: Optimised for mobile and embedded devices + +## Get Started + +1. **Clone Git Repo** + ```bash + git clone https://github.com/neuphonic/neutts-air.git + ``` + ```bash + cd neuttsair + ``` + +2. **Install `espeak` (required dependency)** + + Please refer to the following link for instructions on how to install `espeak`: + + https://github.com/espeak-ng/espeak-ng/blob/master/docs/guide.md + + ```bash + # Mac OS + brew install espeak + + # Ubuntu/Debian + sudo apt install espeak + ``` + + Mac users may need to put the following lines at the top of the neutts.py file. + ```python + from phonemizer.backend.espeak.wrapper import EspeakWrapper + _ESPEAK_LIBRARY = '/opt/homebrew/Cellar/espeak/1.48.04_1/lib/libespeak.1.1.48.dylib' #use the Path to the library. + EspeakWrapper.set_library(_ESPEAK_LIBRARY) + ``` + +3. **Install Python dependencies** + + The requirements file includes the dependencies needed to run the model with PyTorch. + When using an ONNX decoder or a GGML model, some dependencies (such as PyTorch) are no longer required. + + The inference is compatible and tested on `python>=3.11`. + + ``` + pip install -r requirements.txt + ``` + +4. **(Optional) Install Llama-cpp-python to use the `GGUF` models.** + ``` + pip install llama-cpp-python + ``` + To run llama-cpp with GPU suport (CUDA, MPS) support please refer to: + https://pypi.org/project/llama-cpp-python/ + +5. **(Optional) Install onnxruntime to use the `.onnx` decoder.** + If you wnat to run the onnxdecoder + ``` + pip install onnxruntime + ``` + +## Basic Example + +Run the basic example script to synthesize speech: +```bash +python -m examples.basic_example \ + --input_text "My name is Dave, and um, I'm from London" \ + --ref_audio samples/dave.wav \ + --ref_text samples/dave.txt +``` + +To specify a particular model repo for the backbone or codec, add the `--backbone` argument. Available backbones are listed in [NeuTTS-Air huggingface collection](https://huggingface.co/collections/neuphonic/neutts-air-68cc14b7033b4c56197ef350). + +Several examples are available, including a Jupyter notebook in the `examples` folder. + +### Simple One-Code Block Usage + +```python +from neuttsair.neutts import NeuTTSAir +import soundfile as sf + +tts = NeuTTSAir( backbone_repo="neuphonic/neutts-air-q4-gguf", backbone_device="cpu", codec_repo="neuphonic/neucodec", codec_device="cpu") +input_text = "My name is Dave, and um, I'm from London." + +ref_text = "samples/dave.txt" +ref_audio_path = "samples/dave.wav" + +ref_text = open(ref_text, "r").read().strip() +ref_codes = tts.encode_reference(ref_audio_path) + +wav = tts.infer(input_text, ref_codes, ref_text) +sf.write("test.wav", wav, 24000) +``` + + +## Advanced Examples +### GGML Backbone Example +```bash +python -m examples.basic_example \ + --input_text "My name is Dave, and um, I'm from London" \ + --ref_audio ./samples/dave.wav \ + --ref_text ./samples/dave.txt \ + --backbone neuphonic/neutts-air-q4-gguf +``` + +### Onnx Decoder Example + +Make sure you have installed ```onnxruntime``` + +```bash +python -m examples.onnx_example \ + --input_text "My name is Dave, and um, I'm from London" \ + --ref_codes samples/dave.pt \ + --ref_text samples/dave.txt +``` + +To run the model with the onnx decoder you need to encode the reference sample. Please refer to the encode_reference example. + +#### Encode reference +You only need to provide a reference audio for the reference encoding. + +```bash +python -m examples.encode_reference \ + --ref_audio ./samples/dave.wav \ + --output_path encoded_reference.pt + ``` + +## Prepare References for Cloning + +NeuTTS Air requires two inputs: + +1. A reference audio sample (`.wav` file) +2. A text string + +The model then synthesises the text as speech in the style of the reference audio. This is what enables NeuTTS Air’s instant voice cloning capability. + +### Example Reference Files + +You can find some ready-to-use samples in the `examples` folder: + +- `samples/dave.wav` +- `samples/jo.wav` + +### Guidelines for Best Results + +For optimal performance, reference audio samples should be: + +1. **Mono channel** +2. **16-44 kHz sample rate** +3. **3–15 seconds in length** +4. **Saved as a `.wav` file** +5. **Clean** — minimal to no background noise +6. **Natural, continuous speech** — like a monologue or conversation, with few pauses, so the model can capture tone effectively + +## Responsibility + +Every audio file generated by NeuTTS Air includes [Perth (Perceptual Threshold) Watermarker](https://github.com/resemble-ai/perth). + +## Disclaimer + +Don't use this model to do bad things… please. + +## Developer Requirements + +To run the pre commit hooks to contribute to this project run: + +```bash +pip install pre-commit +``` +Then: +```bash +pre-commit install +``` diff --git a/examples/__init__.py b/examples/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/examples/basic_example.py b/examples/basic_example.py new file mode 100644 index 0000000..72180b7 --- /dev/null +++ b/examples/basic_example.py @@ -0,0 +1,76 @@ +import os +import soundfile as sf +from neuttsair.neutts import NeuTTSAir + + +def main(input_text, ref_audio_path, ref_text, backbone, output_path="output.wav"): + if not ref_audio_path or not ref_text: + print("No reference audio or text provided.") + return None + + # Initialize NeuTTSAir with the desired model and codec + tts = NeuTTSAir( + backbone_repo=backbone, + backbone_device="cpu", + codec_repo="neuphonic/neucodec", + codec_device="cpu" + ) + + # Check if ref_text is a path if it is read it if not just return string + if ref_text and os.path.exists(ref_text): + with open(ref_text, "r") as f: + ref_text = f.read().strip() + + print("Encoding reference audio") + ref_codes = tts.encode_reference(ref_audio_path) + + print(f"Generating audio for input text: {input_text}") + wav = tts.infer(input_text, ref_codes, ref_text) + + print(f"Saving output to {output_path}") + sf.write(output_path, wav, 24000) + + +if __name__ == "__main__": + # get arguments from command line + import argparse + + parser = argparse.ArgumentParser(description="NeuTTSAir Example") + parser.add_argument( + "--input_text", + type=str, + required=True, + help="Input text to be converted to speech" + ) + parser.add_argument( + "--ref_audio", + type=str, + default="./samples/dave.wav", + help="Path to reference audio file" + ) + parser.add_argument( + "--ref_text", + type=str, + default="./samples/dave.txt", + help="Reference text corresponding to the reference audio", + ) + parser.add_argument( + "--output_path", + type=str, + default="output.wav", + help="Path to save the output audio" + ) + parser.add_argument( + "--backbone", + type=str, + default="neuphonic/neutts-air", + help="Huggingface repo containing the backbone checkpoint" + ) + args = parser.parse_args() + main( + input_text=args.input_text, + ref_audio_path=args.ref_audio, + ref_text=args.ref_text, + backbone=args.backbone, + output_path=args.output_path, + ) diff --git a/examples/encode_reference.py b/examples/encode_reference.py new file mode 100644 index 0000000..89c6686 --- /dev/null +++ b/examples/encode_reference.py @@ -0,0 +1,47 @@ +# This file contains an example of how to use the NeuTTSAir class to generate codes + +import torch +from librosa import load +from neucodec import NeuCodec + + +def main(ref_audio_path, output_path="output.wav"): + print("Encoding reference audio") + + # Make sure output path ends with .pt + if not output_path.endswith(".pt"): + print("Output path should end with .pt to save the codes.") + return + + # Initialize codec + codec = NeuCodec.from_pretrained("neuphonic/neucodec") + codec.eval().to("cpu") + + # Load and encode reference audio + wav, _ = load(ref_audio_path, sr=16000, mono=True) # load as 16kHz + wav_tensor = torch.from_numpy(wav).float().unsqueeze(0).unsqueeze(0) # [1, 1, T] + ref_codes = codec.encode_code(audio_or_path=wav_tensor).squeeze(0).squeeze(0) + + # Save the codes + torch.save(ref_codes, output_path) + + +if __name__ == "__main__": + # get arguments from command line + import argparse + + parser = argparse.ArgumentParser(description="NeuTTSAir Reference Encoding Example") + parser.add_argument( + "--ref_audio", type=str, default="./samples/dave.wav", help="Path to reference audio" + ) + parser.add_argument( + "--output_path", + type=str, + default="encoded_reference.pt", + help="Path to save the output codes", + ) + args = parser.parse_args() + main( + ref_audio_path=args.ref_audio, + output_path=args.output_path, + ) diff --git a/examples/interactive_example.ipynb b/examples/interactive_example.ipynb new file mode 100644 index 0000000..2b78dcc --- /dev/null +++ b/examples/interactive_example.ipynb @@ -0,0 +1,114 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "a0fa9718", + "metadata": {}, + "source": [ + "Import required libraries" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "939f4fdc", + "metadata": {}, + "outputs": [], + "source": [ + "import sys\n", + "#Append the parent directory to the sys.path to allow imports from neuttsair package\n", + "sys.path.append('..')\n", + "from neuttsair.neutts import NeuTTSAir\n", + "from IPython.display import Audio" + ] + }, + { + "cell_type": "markdown", + "id": "e4e61937", + "metadata": {}, + "source": [ + "Downloads files and loads the model into memory" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "cfabf9dd", + "metadata": {}, + "outputs": [], + "source": [ + "%%capture\n", + "tts = NeuTTSAir(\n", + " backbone_repo=\"neuphonic/neutts-air-q8-gguf\",\n", + " backbone_device=\"cpu\",\n", + " codec_repo=\"neuphonic/neucodec\",\n", + " codec_device=\"cpu\"\n", + ")" + ] + }, + { + "cell_type": "markdown", + "id": "75c87818", + "metadata": {}, + "source": [ + "Pick your speaker and type up your input text - and generate!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "914e5e00", + "metadata": {}, + "outputs": [], + "source": [ + "speaker = \"dave\" # default speakers are 'dave' and 'jo'\n", + "input_text = \"Hey there, I'm Andy. I'm 25 and I just moved to London. The underground is pretty confusing, but it gets me around in no time at all.\"\n", + "\n", + "ref_text = f\"../samples/{speaker}.txt\"\n", + "ref_audio_path = f\"../samples/{speaker}.wav\"\n", + "\n", + "ref_text = open(ref_text, \"r\").read().strip()\n", + "ref_codes = tts.encode_reference(ref_audio_path)\n", + "wav = tts.infer(input_text, ref_codes, ref_text)" + ] + }, + { + "cell_type": "markdown", + "id": "e8da4a9d", + "metadata": {}, + "source": [ + "Listen to your generation!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "21774af1", + "metadata": {}, + "outputs": [], + "source": [ + "Audio(wav, rate=24000)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/examples/onnx_example.py b/examples/onnx_example.py new file mode 100644 index 0000000..afeb05e --- /dev/null +++ b/examples/onnx_example.py @@ -0,0 +1,77 @@ +import os +import soundfile as sf +import torch +from neuttsair.neutts import NeuTTSAir + + +def main(input_text, ref_codes_path, ref_text, backbone, output_path="output.wav"): + if not ref_codes_path or not ref_text: + print("No reference audio or text provided.") + return None + + # Initialize NeuTTSAir with the desired model and codec + tts = NeuTTSAir( + backbone_repo=backbone, + backbone_device="cpu", + codec_repo="neuphonic/neucodec-onnx-decoder", + codec_device="cpu" + ) + + # Check if ref_text is a path if it is read it if not just return string + if ref_text and os.path.exists(ref_text): + with open(ref_text, "r") as f: + ref_text = f.read().strip() + + if ref_codes_path and os.path.exists(ref_codes_path): + ref_codes = torch.load(ref_codes_path) + + print(f"Generating audio for input text: {input_text}") + wav = tts.infer(input_text, ref_codes, ref_text) + + print(f"Saving output to {output_path}") + sf.write(output_path, wav, 24000) + + +if __name__ == "__main__": + # get arguments from command line + import argparse + + parser = argparse.ArgumentParser(description="NeuTTSAir Example") + parser.add_argument( + "--input_text", + type=str, + required=True, + help="Input text to be converted to speech" + ) + parser.add_argument( + "--ref_codes", + type=str, + default="./samples/dave.pt", + help="Path to pre-encoded reference audio" + ) + parser.add_argument( + "--ref_text", + type=str, + default="./samples/dave.txt", + help="Reference text corresponding to the reference audio", + ) + parser.add_argument( + "--output_path", + type=str, + default="output.wav", + help="Path to save the output audio" + ) + parser.add_argument( + "--backbone", + type=str, + default="neuphonic/neutts-air", + help="Huggingface repo containing the backbone checkpoint" + ) + args = parser.parse_args() + main( + input_text=args.input_text, + ref_codes_path=args.ref_codes, + ref_text=args.ref_text, + backbone=args.backbone, + output_path=args.output_path, + ) diff --git a/neuttsair/__init__.py b/neuttsair/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/neuttsair/neutts.py b/neuttsair/neutts.py new file mode 100644 index 0000000..e8a086a --- /dev/null +++ b/neuttsair/neutts.py @@ -0,0 +1,241 @@ +from pathlib import Path +import librosa +import numpy as np +import torch +import re +import perth +from neucodec import NeuCodec, DistillNeuCodec +from phonemizer.backend import EspeakBackend +from transformers import AutoTokenizer, AutoModelForCausalLM + + +class NeuTTSAir: + + def __init__( + self, + backbone_repo="neuphonic/neutts-air", + backbone_device="cpu", + codec_repo="neuphonic/neucodec", + codec_device="cpu", + ): + + # Consts + self.sample_rate = 24_000 + self.max_context = 2048 + + # ggml & onnx flags + self._grammar = None # set with a ggml model + self._is_quantized_model = False + self._is_onnx_codec = False + + # HF tokenizer + self.tokenizer = None + + # Load phonemizer + models + print("Loading phonemizer...") + self.phonemizer = EspeakBackend( + language="en-us", preserve_punctuation=True, with_stress=True + ) + + self._load_backbone(backbone_repo, backbone_device) + + self._load_codec(codec_repo, codec_device) + + # Load watermarker + self.watermarker = perth.PerthImplicitWatermarker() + + def _load_backbone(self, backbone_repo, backbone_device): + print(f"Loading backbone from: {backbone_repo} on {backbone_device} ...") + + # GGUF loading + if backbone_repo.endswith("gguf"): + + try: + from llama_cpp import Llama + except ImportError as e: + raise ImportError( + "Failed to import `llama_cpp`. " + "Please install it with:\n" + " pip install llama-cpp-python" + ) from e + + self.backbone = Llama.from_pretrained( + repo_id=backbone_repo, + filename="*.gguf", + verbose=False, + n_gpu_layers=-1 if backbone_device == "gpu" else 0, + n_ctx=self.max_context, + mlock=True, + flash_attn=True if backbone_device == "gpu" else False, + ) + self._is_quantized_model = True + + else: + self.tokenizer = AutoTokenizer.from_pretrained(backbone_repo) + self.backbone = AutoModelForCausalLM.from_pretrained(backbone_repo).to( + torch.device(backbone_device) + ) + + def _load_codec(self, codec_repo, codec_device): + + print(f"Loading codec from: {codec_repo} on {codec_device} ...") + match codec_repo: + case "neuphonic/neucodec": + self.codec = NeuCodec.from_pretrained(codec_repo) + self.codec.eval().to(codec_device) + case "neuphonic/distill-neucodec": + self.codec = DistillNeuCodec.from_pretrained(codec_repo) + self.codec.eval().to(codec_device) + case "neuphonic/neucodec-onnx-decoder": + + if codec_device != "cpu": + raise ValueError("Onnx decoder only currently runs on CPU.") + + try: + from neucodec import NeuCodecOnnxDecoder + except ImportError as e: + raise ImportError( + "Failed to import the onnx decoder." + " Ensure you have onnxruntime installed as well as neucodec >= 0.0.4." + ) from e + + self.codec = NeuCodecOnnxDecoder.from_pretrained(codec_repo) + self._is_onnx_codec = True + + case _: + raise ValueError( + "Invalid codec repo! Must be one of:" + " 'neuphonic/neucodec', 'neuphonic/distill-neucodec'," + " 'neuphonic/neucodec-onnx-decoder'." + ) + + def infer(self, text: str, ref_codes: np.ndarray | torch.Tensor, ref_text: str) -> np.ndarray: + """ + Perform inference to generate speech from text using the TTS model and reference audio. + + Args: + text (str): Input text to be converted to speech. + ref_codes (np.ndarray | torch.tensor): Encoded reference. + ref_text (str): Reference text for reference audio. Defaults to None. + Returns: + np.ndarray: Generated speech waveform. + """ + + # Generate tokens + if self._is_quantized_model: + output_str = self._infer_ggml(ref_codes, ref_text, text) + else: + prompt_ids = self._apply_chat_template(ref_codes, ref_text, text) + output_str = self._infer_torch(prompt_ids) + + # Decode + wav = self._decode(output_str) + watermarked_wav = self.watermarker.apply_watermark(wav, sample_rate=24_000) + + return watermarked_wav + + def encode_reference(self, ref_audio_path: str | Path): + wav, _ = librosa.load(ref_audio_path, sr=16000, mono=True) + wav_tensor = torch.from_numpy(wav).float().unsqueeze(0).unsqueeze(0) # [1, 1, T] + ref_codes = self.codec.encode_code(audio_or_path=wav_tensor).squeeze(0).squeeze(0) + return ref_codes + + def _decode(self, codes: str): + + # Extract speech token IDs using regex + speech_ids = [int(num) for num in re.findall(r"<\|speech_(\d+)\|>", codes)] + + if len(speech_ids) > 0: + + # Onnx decode + if self._is_onnx_codec: + codes = np.array(speech_ids, dtype=np.int32)[np.newaxis, np.newaxis, :] + recon = self.codec.decode_code(codes) + + # Torch decode + else: + with torch.no_grad(): + codes = torch.tensor(speech_ids, dtype=torch.long)[None, None, :].to( + self.codec.device + ) + recon = self.codec.decode_code(codes).cpu().numpy() + + return recon[0, 0, :] + else: + raise ValueError("No valid speech tokens found in the output.") + + def _to_phones(self, text: str) -> str: + phones = self.phonemizer.phonemize([text]) + phones = phones[0].split() + phones = " ".join(phones) + return phones + + def _apply_chat_template( + self, ref_codes: list[int], ref_text: str, input_text: str + ) -> list[int]: + + input_text = self._to_phones(ref_text) + " " + self._to_phones(input_text) + speech_replace = self.tokenizer.convert_tokens_to_ids("<|SPEECH_REPLACE|>") + speech_gen_start = self.tokenizer.convert_tokens_to_ids("<|SPEECH_GENERATION_START|>") + text_replace = self.tokenizer.convert_tokens_to_ids("<|TEXT_REPLACE|>") + text_prompt_start = self.tokenizer.convert_tokens_to_ids("<|TEXT_PROMPT_START|>") + text_prompt_end = self.tokenizer.convert_tokens_to_ids("<|TEXT_PROMPT_END|>") + + input_ids = self.tokenizer.encode(input_text, add_special_tokens=False) + chat = """user: Convert the text to speech:<|TEXT_REPLACE|>\nassistant:<|SPEECH_REPLACE|>""" + ids = self.tokenizer.encode(chat) + + text_replace_idx = ids.index(text_replace) + ids = ( + ids[:text_replace_idx] + + [text_prompt_start] + + input_ids + + [text_prompt_end] + + ids[text_replace_idx + 1 :] # noqa + ) + + speech_replace_idx = ids.index(speech_replace) + codes_str = "".join([f"<|speech_{i}|>" for i in ref_codes]) + codes = self.tokenizer.encode(codes_str, add_special_tokens=False) + ids = ids[:speech_replace_idx] + [speech_gen_start] + list(codes) + + return ids + + def _infer_torch(self, prompt_ids: list[int]) -> str: + prompt_tensor = torch.tensor(prompt_ids).unsqueeze(0).to(self.backbone.device) + speech_end_id = self.tokenizer.convert_tokens_to_ids("<|SPEECH_GENERATION_END|>") + with torch.no_grad(): + output_tokens = self.backbone.generate( + prompt_tensor, + max_length=self.max_context, + eos_token_id=speech_end_id, + do_sample=True, + temperature=1.0, + top_k=50, + use_cache=True, + min_new_tokens=50, + ) + input_length = prompt_tensor.shape[-1] + output_str = self.tokenizer.decode( + output_tokens[0, input_length:].cpu().numpy().tolist(), add_special_tokens=False + ) + return output_str + + def _infer_ggml(self, ref_codes: list[int], ref_text: str, input_text: str) -> str: + ref_text = self._to_phones(ref_text) + input_text = self._to_phones(input_text) + + codes_str = "".join([f"<|speech_{idx}|>" for idx in ref_codes]) + prompt = ( + f"user: Convert the text to speech:<|TEXT_PROMPT_START|>{ref_text} {input_text}" + f"<|TEXT_PROMPT_END|>\nassistant:<|SPEECH_GENERATION_START|>{codes_str}" + ) + output = self.backbone( + prompt, + max_tokens=self.max_context, + temperature=1.0, + top_k=50, + stop=["<|SPEECH_GENERATION_END|>"], + ) + output_str = output["choices"][0]["text"] + return output_str diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..bc72308 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,18 @@ +datasets==4.0.0 +librosa==0.11.0 +neucodec>=0.0.3 +numpy==2.2.6 +pandas==2.3.2 +phonemizer==3.3.0 +requests==2.32.5 +scipy>=1.15 +soundfile==0.13.1 +torch==2.8.0 +torchao==0.13.0 +torchaudio==2.8.0 +torchtune==0.6.1 +tqdm==4.67.1 +transformers==4.56.1 +vector-quantize-pytorch==1.17.8 +resemble-perth==1.0.1 +accelerate==1.10.1 \ No newline at end of file diff --git a/samples/dave.pt b/samples/dave.pt new file mode 100644 index 0000000..5a24d85 Binary files /dev/null and b/samples/dave.pt differ diff --git a/samples/dave.txt b/samples/dave.txt new file mode 100644 index 0000000..f5bdcac --- /dev/null +++ b/samples/dave.txt @@ -0,0 +1 @@ +So I'm live on radio. And I say, well, my dear friend James here clearly, and the whole room just froze. Turns out I'd completely misspoken and mentioned our other friend. diff --git a/samples/dave.wav b/samples/dave.wav new file mode 100644 index 0000000..fa77b53 Binary files /dev/null and b/samples/dave.wav differ diff --git a/samples/jo.pt b/samples/jo.pt new file mode 100644 index 0000000..a8275be Binary files /dev/null and b/samples/jo.pt differ diff --git a/samples/jo.txt b/samples/jo.txt new file mode 100644 index 0000000..6a6a43d --- /dev/null +++ b/samples/jo.txt @@ -0,0 +1 @@ +So I just tried Neuphonic and I’m genuinely impressed. It's super responsive, it sounds clean, supports voice cloning, and the agent feature is fun to play with too. Highly recommend it for podcasts, conversations, or even just messing around with voiceovers. diff --git a/samples/jo.wav b/samples/jo.wav new file mode 100644 index 0000000..059b94f Binary files /dev/null and b/samples/jo.wav differ