Upload 9 files

.gitignore

@@ -0,0 +1,171 @@
+# Customed
+.vscode/
+tests/
+runs/
+data/
+ckpts/
+wandb/
+results/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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
+.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/

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "src/third_party/BigVGAN"]
+	path = src/third_party/BigVGAN
+	url = https://github.com/NVIDIA/BigVGAN.git

.pre-commit-config.yaml

@@ -0,0 +1,17 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.11.2
+    hooks:
+      - id: ruff
+        name: ruff linter
+        args: [--fix]
+      - id: ruff-format
+        name: ruff formatter
+      - id: ruff
+        name: ruff sorter
+        args: [--select, I, --fix]
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-yaml

Dockerfile

@@ -0,0 +1,30 @@
+FROM pytorch/pytorch:2.4.0-cuda12.4-cudnn9-devel
+
+USER root
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+LABEL github_repo="https://github.com/SWivid/F5-TTS"
+
+RUN set -x \
+    && apt-get update \
+    && apt-get -y install wget curl man git less openssl libssl-dev unzip unar build-essential aria2 tmux vim \
+    && apt-get install -y openssh-server sox libsox-fmt-all libsox-fmt-mp3 libsndfile1-dev ffmpeg \
+    && apt-get install -y librdmacm1 libibumad3 librdmacm-dev libibverbs1 libibverbs-dev ibverbs-utils ibverbs-providers \
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get clean
+    
+WORKDIR /workspace
+
+RUN git clone https://github.com/SWivid/F5-TTS.git \
+    && cd F5-TTS \
+    && git submodule update --init --recursive \
+    && pip install -e . --no-cache-dir
+
+ENV SHELL=/bin/bash
+
+VOLUME /root/.cache/huggingface/hub/
+
+EXPOSE 7860
+
+WORKDIR /workspace/F5-TTS

F5-TTS-main.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8a5e583db3435098285e15cb2bfb675c87cc816d3ddd62b2986728959cd5a2
+size 1407856

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Yushen CHEN
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,13 +1,261 @@
----
-title: Audio F5TTS
-emoji: 📉
-colorFrom: gray
-colorTo: green
-sdk: gradio
-sdk_version: 5.43.1
-app_file: app.py
-pinned: false
-short_description: open-source Text-to-Speech (TTS) model.
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
+
+[![python](https://img.shields.io/badge/Python-3.10-brightgreen)](https://github.com/SWivid/F5-TTS)
+[![arXiv](https://img.shields.io/badge/arXiv-2410.06885-b31b1b.svg?logo=arXiv)](https://arxiv.org/abs/2410.06885)
+[![demo](https://img.shields.io/badge/GitHub-Demo%20page-orange.svg)](https://swivid.github.io/F5-TTS/)
+[![hfspace](https://img.shields.io/badge/🤗-Space%20demo-yellow)](https://huggingface.co/spaces/mrfakename/E2-F5-TTS)
+[![msspace](https://img.shields.io/badge/🤖-Space%20demo-blue)](https://modelscope.cn/studios/modelscope/E2-F5-TTS)
+[![lab](https://img.shields.io/badge/X--LANCE-Lab-grey?labelColor=lightgrey)](https://x-lance.sjtu.edu.cn/)
+[![lab](https://img.shields.io/badge/Peng%20Cheng-Lab-grey?labelColor=lightgrey)](https://www.pcl.ac.cn)
+<!-- <img src="https://github.com/user-attachments/assets/12d7749c-071a-427c-81bf-b87b91def670" alt="Watermark" style="width: 40px; height: auto"> -->
+
+**F5-TTS**: Diffusion Transformer with ConvNeXt V2, faster trained and inference.
+
+**E2 TTS**: Flat-UNet Transformer, closest reproduction from [paper](https://arxiv.org/abs/2406.18009).
+
+**Sway Sampling**: Inference-time flow step sampling strategy, greatly improves performance
+
+### Thanks to all the contributors !
+
+## News
+- **2025/03/12**: 🔥 F5-TTS v1 base model with better training and inference performance. [Few demo](https://swivid.github.io/F5-TTS_updates).
+- **2024/10/08**: F5-TTS & E2 TTS base models on [🤗 Hugging Face](https://huggingface.co/SWivid/F5-TTS), [🤖 Model Scope](https://www.modelscope.cn/models/SWivid/F5-TTS_Emilia-ZH-EN), [🟣 Wisemodel](https://wisemodel.cn/models/SJTU_X-LANCE/F5-TTS_Emilia-ZH-EN).
+
+## Installation
+
+### Create a separate environment if needed
+
+```bash
+# Create a python 3.10 conda env (you could also use virtualenv)
+conda create -n f5-tts python=3.10
+conda activate f5-tts
+```
+
+### Install PyTorch with matched device
+
+<details>
+<summary>NVIDIA GPU</summary>
+
+> ```bash
+> # Install pytorch with your CUDA version, e.g.
+> pip install torch==2.4.0+cu124 torchaudio==2.4.0+cu124 --extra-index-url https://download.pytorch.org/whl/cu124
+> ```
+
+</details>
+
+<details>
+<summary>AMD GPU</summary>
+
+> ```bash
+> # Install pytorch with your ROCm version (Linux only), e.g.
+> pip install torch==2.5.1+rocm6.2 torchaudio==2.5.1+rocm6.2 --extra-index-url https://download.pytorch.org/whl/rocm6.2
+> ```
+
+</details>
+
+<details>
+<summary>Intel GPU</summary>
+
+> ```bash
+> # Install pytorch with your XPU version, e.g.
+> # Intel® Deep Learning Essentials or Intel® oneAPI Base Toolkit must be installed
+> pip install torch torchaudio --index-url https://download.pytorch.org/whl/test/xpu
+> 
+> # Intel GPU support is also available through IPEX (Intel® Extension for PyTorch)
+> # IPEX does not require the Intel® Deep Learning Essentials or Intel® oneAPI Base Toolkit
+> # See: https://pytorch-extension.intel.com/installation?request=platform
+> ```
+
+</details>
+
+<details>
+<summary>Apple Silicon</summary>
+
+> ```bash
+> # Install the stable pytorch, e.g.
+> pip install torch torchaudio
+> ```
+
+</details>
+
+### Then you can choose one from below:
+
+> ### 1. As a pip package (if just for inference)
+> 
+> ```bash
+> pip install f5-tts
+> ```
+> 
+> ### 2. Local editable (if also do training, finetuning)
+> 
+> ```bash
+> git clone https://github.com/SWivid/F5-TTS.git
+> cd F5-TTS
+> # git submodule update --init --recursive  # (optional, if use bigvgan as vocoder)
+> pip install -e .
+> ```
+
+### Docker usage also available
+```bash
+# Build from Dockerfile
+docker build -t f5tts:v1 .
+
+# Run from GitHub Container Registry
+docker container run --rm -it --gpus=all --mount 'type=volume,source=f5-tts,target=/root/.cache/huggingface/hub/' -p 7860:7860 ghcr.io/swivid/f5-tts:main
+
+# Quickstart if you want to just run the web interface (not CLI)
+docker container run --rm -it --gpus=all --mount 'type=volume,source=f5-tts,target=/root/.cache/huggingface/hub/' -p 7860:7860 ghcr.io/swivid/f5-tts:main f5-tts_infer-gradio --host 0.0.0.0
+```
+
+### Runtime
+
+Deployment solution with Triton and TensorRT-LLM.
+
+#### Benchmark Results
+Decoding on a single L20 GPU, using 26 different prompt_audio & target_text pairs, 16 NFE.
+
+| Model               | Concurrency    | Avg Latency | RTF    | Mode            |
+|---------------------|----------------|-------------|--------|-----------------|
+| F5-TTS Base (Vocos) | 2              | 253 ms      | 0.0394 | Client-Server   |
+| F5-TTS Base (Vocos) | 1 (Batch_size) | -           | 0.0402 | Offline TRT-LLM |
+| F5-TTS Base (Vocos) | 1 (Batch_size) | -           | 0.1467 | Offline Pytorch |
+
+See [detailed instructions](src/f5_tts/runtime/triton_trtllm/README.md) for more information.
+
+
+## Inference
+
+- In order to achieve desired performance, take a moment to read [detailed guidance](src/f5_tts/infer).
+- By properly searching the keywords of problem encountered, [issues](https://github.com/SWivid/F5-TTS/issues?q=is%3Aissue) are very helpful.
+
+### 1. Gradio App
+
+Currently supported features:
+
+- Basic TTS with Chunk Inference
+- Multi-Style / Multi-Speaker Generation
+- Voice Chat powered by Qwen2.5-3B-Instruct
+- [Custom inference with more language support](src/f5_tts/infer/SHARED.md)
+
+```bash
+# Launch a Gradio app (web interface)
+f5-tts_infer-gradio
+
+# Specify the port/host
+f5-tts_infer-gradio --port 7860 --host 0.0.0.0
+
+# Launch a share link
+f5-tts_infer-gradio --share
+```
+
+<details>
+<summary>NVIDIA device docker compose file example</summary>
+
+```yaml
+services:
+  f5-tts:
+    image: ghcr.io/swivid/f5-tts:main
+    ports:
+      - "7860:7860"
+    environment:
+      GRADIO_SERVER_PORT: 7860
+    entrypoint: ["f5-tts_infer-gradio", "--port", "7860", "--host", "0.0.0.0"]
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+
+volumes:
+  f5-tts:
+    driver: local
+```
+
+</details>
+
+### 2. CLI Inference
+
+```bash
+# Run with flags
+# Leave --ref_text "" will have ASR model transcribe (extra GPU memory usage)
+f5-tts_infer-cli --model F5TTS_v1_Base \
+--ref_audio "provide_prompt_wav_path_here.wav" \
+--ref_text "The content, subtitle or transcription of reference audio." \
+--gen_text "Some text you want TTS model generate for you."
+
+# Run with default setting. src/f5_tts/infer/examples/basic/basic.toml
+f5-tts_infer-cli
+# Or with your own .toml file
+f5-tts_infer-cli -c custom.toml
+
+# Multi voice. See src/f5_tts/infer/README.md
+f5-tts_infer-cli -c src/f5_tts/infer/examples/multi/story.toml
+```
+
+
+## Training
+
+### 1. With Hugging Face Accelerate
+
+Refer to [training & finetuning guidance](src/f5_tts/train) for best practice.
+
+### 2. With Gradio App
+
+```bash
+# Quick start with Gradio web interface
+f5-tts_finetune-gradio
+```
+
+Read [training & finetuning guidance](src/f5_tts/train) for more instructions.
+
+
+## [Evaluation](src/f5_tts/eval)
+
+
+## Development
+
+Use pre-commit to ensure code quality (will run linters and formatters automatically):
+
+```bash
+pip install pre-commit
+pre-commit install
+```
+
+When making a pull request, before each commit, run: 
+
+```bash
+pre-commit run --all-files
+```
+
+Note: Some model components have linting exceptions for E722 to accommodate tensor notation.
+
+
+## Acknowledgements
+
+- [E2-TTS](https://arxiv.org/abs/2406.18009) brilliant work, simple and effective
+- [Emilia](https://arxiv.org/abs/2407.05361), [WenetSpeech4TTS](https://arxiv.org/abs/2406.05763), [LibriTTS](https://arxiv.org/abs/1904.02882), [LJSpeech](https://keithito.com/LJ-Speech-Dataset/) valuable datasets
+- [lucidrains](https://github.com/lucidrains) initial CFM structure with also [bfs18](https://github.com/bfs18) for discussion
+- [SD3](https://arxiv.org/abs/2403.03206) & [Hugging Face diffusers](https://github.com/huggingface/diffusers) DiT and MMDiT code structure
+- [torchdiffeq](https://github.com/rtqichen/torchdiffeq) as ODE solver, [Vocos](https://huggingface.co/charactr/vocos-mel-24khz) and [BigVGAN](https://github.com/NVIDIA/BigVGAN) as vocoder
+- [FunASR](https://github.com/modelscope/FunASR), [faster-whisper](https://github.com/SYSTRAN/faster-whisper), [UniSpeech](https://github.com/microsoft/UniSpeech), [SpeechMOS](https://github.com/tarepan/SpeechMOS) for evaluation tools
+- [ctc-forced-aligner](https://github.com/MahmoudAshraf97/ctc-forced-aligner) for speech edit test
+- [mrfakename](https://x.com/realmrfakename) huggingface space demo ~
+- [f5-tts-mlx](https://github.com/lucasnewman/f5-tts-mlx/tree/main) Implementation with MLX framework by [Lucas Newman](https://github.com/lucasnewman)
+- [F5-TTS-ONNX](https://github.com/DakeQQ/F5-TTS-ONNX) ONNX Runtime version by [DakeQQ](https://github.com/DakeQQ)
+- [Yuekai Zhang](https://github.com/yuekaizhang) Triton and TensorRT-LLM support ~
+
+## Citation
+If our work and codebase is useful for you, please cite as:
+```
+@article{chen-etal-2024-f5tts,
+      title={F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching}, 
+      author={Yushen Chen and Zhikang Niu and Ziyang Ma and Keqi Deng and Chunhui Wang and Jian Zhao and Kai Yu and Xie Chen},
+      journal={arXiv preprint arXiv:2410.06885},
+      year={2024},
+}
+```
+## License
+
+Our code is released under MIT License. The pre-trained models are licensed under the CC-BY-NC license due to the training data Emilia, which is an in-the-wild dataset. Sorry for any inconvenience this may cause.

pyproject.toml

@@ -0,0 +1,64 @@
+[build-system]
+requires = ["setuptools >= 61.0", "setuptools-scm>=8.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "f5-tts"
+version = "1.1.7"
+description = "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
+readme = "README.md"
+license = {text = "MIT License"}
+classifiers = [
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+]
+dependencies = [
+    "accelerate>=0.33.0",
+    "bitsandbytes>0.37.0; platform_machine != 'arm64' and platform_system != 'Darwin'",
+    "cached_path",
+    "click",
+    "datasets",
+    "ema_pytorch>=0.5.2",
+    "gradio>=3.45.2",
+    "hydra-core>=1.3.0",
+    "jieba",
+    "librosa",
+    "matplotlib",
+    "numpy<=1.26.4",
+    "pydantic<=2.10.6",
+    "pydub",
+    "pypinyin",
+    "safetensors",
+    "soundfile",
+    "tomli",
+    "torch>=2.0.0",
+    "torchaudio>=2.0.0",
+    "torchdiffeq",
+    "tqdm>=4.65.0",
+    "transformers",
+    "transformers_stream_generator",
+    "unidecode",
+    "vocos",
+    "wandb",
+    "x_transformers>=1.31.14",
+]
+
+[project.optional-dependencies]
+eval = [
+    "faster_whisper==0.10.1",
+    "funasr",
+    "jiwer",
+    "modelscope",
+    "zhconv",
+    "zhon",
+]
+
+[project.urls]
+Homepage = "https://github.com/SWivid/F5-TTS"
+
+[project.scripts]
+"f5-tts_infer-cli" = "f5_tts.infer.infer_cli:main"
+"f5-tts_infer-gradio" = "f5_tts.infer.infer_gradio:main"
+"f5-tts_finetune-cli" = "f5_tts.train.finetune_cli:main"
+"f5-tts_finetune-gradio" = "f5_tts.train.finetune_gradio:main"

ruff.toml

@@ -0,0 +1,10 @@
+line-length = 120
+target-version = "py310"
+
+[lint]
+# Only ignore variables with names starting with "_".
+dummy-variable-rgx = "^_.*$"
+
+[lint.isort]
+force-single-line = false
+lines-after-imports = 2