F5-TTS: Diffusion Transformer with ConvNeXt V2, faster trained and inference.
E2 TTS: Flat-UNet Transformer, closest reproduction from paper.
Sway Sampling: Inference-time flow step sampling strategy, greatly improves performance
- 2025/03/12: š„ F5-TTS v1 base model with better training and inference performance. Few demo.
- 2024/10/08: F5-TTS & E2 TTS base models on š¤ Hugging Face, š¤ Model Scope, š£ Wisemodel.
# Create a python 3.10 conda env (you could also use virtualenv)
conda create -n f5-tts python=3.10
conda activate f5-ttsNVIDIA GPU
# 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
AMD GPU
# 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
Intel GPU
# Install pytorch with your XPU version, e.g. # IntelĀ® Deep Learning Essentials or IntelĀ® 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 (IntelĀ® Extension for PyTorch) # IPEX does not require the IntelĀ® Deep Learning Essentials or IntelĀ® oneAPI Base Toolkit # See: https://pytorch-extension.intel.com/installation?request=platform
Apple Silicon
# Install the stable pytorch, e.g. pip install torch torchaudio
1. As a pip package (if just for inference)
pip install f5-ttsgit clone https://github.com/SWivid/F5-TTS.git cd F5-TTS # git submodule update --init --recursive # (optional, if need > bigvgan) pip install -e .# 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 0.0.0.0Deployment solution with Triton and TensorRT-LLM.
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 for more information.
- In order to achieve desired performance, take a moment to read detailed guidance.
- By properly searching the keywords of problem encountered, issues are very helpful.
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
# 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 --shareNVIDIA device docker compose file example
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# 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.tomlRefer to training & finetuning guidance for best practice.
# Quick start with Gradio web interface f5-tts_finetune-gradioRead training & finetuning guidance for more instructions.
Use pre-commit to ensure code quality (will run linters and formatters automatically):
pip install pre-commit pre-commit installWhen making a pull request, before each commit, run:
pre-commit run --all-filesNote: Some model components have linting exceptions for E722 to accommodate tensor notation.
- E2-TTS brilliant work, simple and effective
- Emilia, WenetSpeech4TTS, LibriTTS, LJSpeech valuable datasets
- lucidrains initial CFM structure with also bfs18 for discussion
- SD3 & Hugging Face diffusers DiT and MMDiT code structure
- torchdiffeq as ODE solver, Vocos and BigVGAN as vocoder
- FunASR, faster-whisper, UniSpeech, SpeechMOS for evaluation tools
- ctc-forced-aligner for speech edit test
- mrfakename huggingface space demo ~
- f5-tts-mlx Implementation with MLX framework by Lucas Newman
- F5-TTS-ONNX ONNX Runtime version by DakeQQ
- Yuekai Zhang Triton and TensorRT-LLM support ~
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}, }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.