--- base_model: myshell-ai/OpenVoiceV2 base_model_relation: quantized license: mit pipeline_tag: audio-to-audio library_name: onnx tags: - onnx - moonbox - onnxruntime - openvoice - voice-conversion - tone-color-converter - multilingual --- # OpenVoice V2 ONNX ONNX builds of [OpenVoice V2](https://huggingface.co/myshell-ai/OpenVoiceV2), made by Moonbox for on-device use with ONNX Runtime (CPU, CUDA, DirectML). Each precision is one folder holding the graphs and a small Python `pipeline.py` that does the rest (features, resampling, the conversion steps); what the graphs take and return is under *How to run*. ## Files The last column is the benchmark on Moonbox's voice-conversion set (English LibriSpeech and Chinese AISHELL-1 recordings, each converted into an English and a Chinese target voice; details under *How to run*): error rate of a Whisper transcript of the output against the source's transcript, speaker similarity to the target voice and DNSMOS, against the original PyTorch model. | Precision | File | Size | sha256 | Benchmark | |---|---|---|---|---| | fp16 | [`fp16/config.json`](https://huggingface.co/moonbox-dev/OpenVoiceV2-ONNX/blob/main/fp16/config.json) | 0.8 kB | `9dfff60350b8` | WER 2.6 % / CER 25.0 % (original 2.6 / 27.1, fp32), similarity 0.842 / 0.792 (0.842 / 0.797), DNSMOS 3.31 / 2.90 (3.30 / 2.89); SNR 23 dB vs original; RTF 0.06 (CUDA) | | fp16 | [`fp16/converter.onnx`](https://huggingface.co/moonbox-dev/OpenVoiceV2-ONNX/blob/main/fp16/converter.onnx) | 64.3 MB | `22a79ab872d1` | WER 2.6 % / CER 25.0 % (original 2.6 / 27.1, fp32), similarity 0.842 / 0.792 (0.842 / 0.797), DNSMOS 3.31 / 2.90 (3.30 / 2.89); SNR 23 dB vs original; RTF 0.06 (CUDA) | | fp16 | [`fp16/pipeline.py`](https://huggingface.co/moonbox-dev/OpenVoiceV2-ONNX/blob/main/fp16/pipeline.py) | 3.7 kB | `876563834920` | WER 2.6 % / CER 25.0 % (original 2.6 / 27.1, fp32), similarity 0.842 / 0.792 (0.842 / 0.797), DNSMOS 3.31 / 2.90 (3.30 / 2.89); SNR 23 dB vs original; RTF 0.06 (CUDA) | | fp16 | [`fp16/ref_encoder.onnx`](https://huggingface.co/moonbox-dev/OpenVoiceV2-ONNX/blob/main/fp16/ref_encoder.onnx) | 1.6 MB | `50742432520f` | WER 2.6 % / CER 25.0 % (original 2.6 / 27.1, fp32), similarity 0.842 / 0.792 (0.842 / 0.797), DNSMOS 3.31 / 2.90 (3.30 / 2.89); SNR 23 dB vs original; RTF 0.06 (CUDA) | | int8 | [`int8/config.json`](https://huggingface.co/moonbox-dev/OpenVoiceV2-ONNX/blob/main/int8/config.json) | 0.8 kB | `9dfff60350b8` | WER 2.6 % / CER 25.0 %, similarity 0.845 / 0.789, DNSMOS 3.30 / 2.89; SNR 5 dB vs original; RTF 0.04 (CUDA) | | int8 | [`int8/converter.onnx`](https://huggingface.co/moonbox-dev/OpenVoiceV2-ONNX/blob/main/int8/converter.onnx) | 32.7 MB | `17c254cb33ca` | WER 2.6 % / CER 25.0 %, similarity 0.845 / 0.789, DNSMOS 3.30 / 2.89; SNR 5 dB vs original; RTF 0.04 (CUDA) | | int8 | [`int8/pipeline.py`](https://huggingface.co/moonbox-dev/OpenVoiceV2-ONNX/blob/main/int8/pipeline.py) | 3.7 kB | `876563834920` | WER 2.6 % / CER 25.0 %, similarity 0.845 / 0.789, DNSMOS 3.30 / 2.89; SNR 5 dB vs original; RTF 0.04 (CUDA) | | int8 | [`int8/ref_encoder.onnx`](https://huggingface.co/moonbox-dev/OpenVoiceV2-ONNX/blob/main/int8/ref_encoder.onnx) | 0.8 MB | `2e8b8b34c880` | WER 2.6 % / CER 25.0 %, similarity 0.845 / 0.789, DNSMOS 3.30 / 2.89; SNR 5 dB vs original; RTF 0.04 (CUDA) | ## How to run OpenVoice V2's tone-colour converter (MyShell: re-voices a recording into the voice of a reference recording, keeping its words and timing; any language, 22.05 kHz output) as two ONNX graphs plus `pipeline.py`, a numpy runtime that reproduces the official `ToneColorConverter.extract_se` / `convert(tau=0.3)` around them. The base speakers (MeloTTS) are not part of this repository: give it any recording as the source. - `ref_encoder.onnx`: linear spectrogram `spec` [1, T, 513] (22.05 kHz, n_fft 1024, hop 256) -> tone-colour embedding `se` [1, 256]. - `converter.onnx`: the source's spectrogram `spec` [1, 513, T], the posterior encoder's sampling noise `noise` [1, 192, T], and the source and target embeddings `src_se`, `tgt_se` [1, 256, 1] -> audio `wav` [1, 1, 256 T] (the original `SynthesizerTrn.voice_conversion` with tau 0.3). The noise is an input, so a seed gives the same output every run. `pipeline.py` computes the spectrogram in numpy (the original's `spectrogram_torch(center=False)`), resamples with soxr, and embeds the source and the target voice each in one piece (the official `se_extractor.get_se` first splits the reference with a VAD and averages; for a long reference you can do the same with `embed` and average the embeddings). The watermark the official code can add is not included. It needs numpy, onnxruntime (or onnxruntime-gpu), soundfile and soxr: ```bash python fp16/pipeline.py source.wav voice.wav out.wav --cuda --seed 0 ``` ```python import sys, soundfile as sf sys.path.insert(0, "fp16") import pipeline vc = pipeline.OpenVoiceV2("fp16", "cuda") src, sr = sf.read("source.wav", dtype="float32") ref, ref_sr = sf.read("voice.wav", dtype="float32") wav, out_sr = vc(src, sr, ref, ref_sr, seed=0) # 22.05 kHz ``` **Precisions.** `fp16/`: both graphs fp16 math with fp32 inputs and outputs (66 MB). `int8/`: weight-only int8 for every convolution, GRU and linear layer, fp32 math (34 MB). No bf16 build, and no int4: the model has no MatMul weights for 4-bit MatMulNBits. **Benchmark.** The lab's voice-conversion set: 4 English recordings (LibriSpeech test-clean) and 2 Chinese ones (AISHELL-1 test), each converted into the English (LibriSpeech) and the Chinese (AISHELL-1) voice of the lab's TTS prompts: 12 conversions. Each output is judged by Whisper large-v3-turbo's WER (English sources) or CER (Chinese) against the source's transcript, WavLM-base-plus-sv speaker similarity to the target voice, and DNSMOS (P.835 overall). The original is the official code (openvoice @ 74a1d14) in fp32 on CUDA, given the same noise and the same spectrograms as the graphs. Pass, per source language: error rate at most 2 points above the original's, similarity at most 0.03 below, DNSMOS at most 0.2 below. Real-time factor (processing time / audio time) on an RTX 3080 Laptop GPU, whole pipeline. SNR is each output against the original's on the same input and noise. | | English WER | similarity | DNSMOS | Chinese CER | similarity | DNSMOS | SNR vs original | Real-time factor | |---|---|---|---|---|---|---|---|---| | original (PyTorch fp32, CUDA) | 2.6 % | 0.842 | 3.30 | 27.1 % | 0.797 | 2.89 | | 0.05 | | `fp16/` (CUDA) | 2.6 % | 0.842 | 3.31 | 25.0 % | 0.792 | 2.90 | 23 dB | 0.06 | | `int8/` (CUDA) | 2.6 % | 0.845 | 3.30 | 25.0 % | 0.789 | 2.89 | 5 dB | 0.04 | The Chinese error rate is high for the original too: the two AISHELL-1 sources are about 4 s each, and the converter slurs some characters. The int8 output differs audibly in detail from the original's (low SNR) while scoring the same; use `fp16/` if you need it close to the original sample by sample. The fp32 graphs, checked before the ladder, match the original to 5e-6 (converter) and 1e-6 (reference encoder), 39 dB SNR on this set on CUDA. ## How these were made From [OpenVoice V2](https://huggingface.co/myshell-ai/OpenVoiceV2) at revision `f36e7ed`. The graphs were exported from the original PyTorch modules with torch.onnx (opset 17 / 18) and checked against them. Weight-only quantization: int8 is a per-output-channel int8 weight behind DequantizeLinear, int4 is ONNX Runtime's MatMulNBits (block 32). Each card above says which precision every graph uses. Every precision was benchmarked against the original before upload (pass, per language: error rate at most 2 points above the original's, similarity to the target voice at most 0.03 below, DNSMOS at most 0.2 below), and the `sha256` column above is what the files must hash to. ## License MIT. These files are a derivative of the original model and carry its license: it is copied in this repository, and it governs your use of these files. The original model card follows unchanged. --- # Original model card # OpenVoice V2 myshell-ai%2FOpenVoice | Trendshift In April 2024, we release OpenVoice V2, which includes all features in V1 and has: 1. Better Audio Quality. OpenVoice V2 adopts a different training strategy that delivers better audio quality. 2. Native Multi-lingual Support. English, Spanish, French, Chinese, Japanese and Korean are natively supported in OpenVoice V2. 3. Free Commercial Use. Starting from April 2024, both V2 and V1 are released under MIT License. Free for commercial use. ### Features - **Accurate Tone Color Cloning.** OpenVoice can accurately clone the reference tone color and generate speech in multiple languages and accents. - **Flexible Voice Style Control.** OpenVoice enables granular control over voice styles, such as emotion and accent, as well as other style parameters including rhythm, pauses, and intonation. - **Zero-shot Cross-lingual Voice Cloning.** Neither of the language of the generated speech nor the language of the reference speech needs to be presented in the massive-speaker multi-lingual training dataset. ### How to Use Please see [usage](https://github.com/myshell-ai/OpenVoice/blob/main/docs/USAGE.md) for detailed instructions. # Usage ## Table of Content - [Quick Use](#quick-use): directly use OpenVoice without installation. - [Linux Install](#linux-install): for researchers and developers only. - [V1](#openvoice-v1) - [V2](#openvoice-v2) - [Install on Other Platforms](#install-on-other-platforms): unofficial installation guide contributed by the community ## Quick Use The input speech audio of OpenVoice can be in **Any Language**. OpenVoice can clone the voice in that speech audio, and use the voice to speak in multiple languages. For quick use, we recommend you to try the already deployed services: - [British English](https://app.myshell.ai/widget/vYjqae) - [American English](https://app.myshell.ai/widget/nEFFJf) - [Indian English](https://app.myshell.ai/widget/V3iYze) - [Australian English](https://app.myshell.ai/widget/fM7JVf) - [Spanish](https://app.myshell.ai/widget/NNFFVz) - [French](https://app.myshell.ai/widget/z2uyUz) - [Chinese](https://app.myshell.ai/widget/fU7nUz) - [Japanese](https://app.myshell.ai/widget/IfIB3u) - [Korean](https://app.myshell.ai/widget/q6ZjIn) ## Linux Install This section is only for developers and researchers who are familiar with Linux, Python and PyTorch. Clone this repo, and run ``` conda create -n openvoice python=3.9 conda activate openvoice git clone git@github.com:myshell-ai/OpenVoice.git cd OpenVoice pip install -e . ``` No matter if you are using V1 or V2, the above installation is the same. ### OpenVoice V1 Download the checkpoint from [here](https://myshell-public-repo-host.s3.amazonaws.com/openvoice/checkpoints_1226.zip) and extract it to the `checkpoints` folder. **1. Flexible Voice Style Control.** Please see [`demo_part1.ipynb`](https://github.com/myshell-ai/OpenVoice/blob/main/demo_part1.ipynb) for an example usage of how OpenVoice enables flexible style control over the cloned voice. **2. Cross-Lingual Voice Cloning.** Please see [`demo_part2.ipynb`](https://github.com/myshell-ai/OpenVoice/blob/main/demo_part2.ipynb) for an example for languages seen or unseen in the MSML training set. **3. Gradio Demo.**. We provide a minimalist local gradio demo here. We strongly suggest the users to look into `demo_part1.ipynb`, `demo_part2.ipynb` and the [QnA](QA.md) if they run into issues with the gradio demo. Launch a local gradio demo with `python -m openvoice_app --share`. ### OpenVoice V2 Download the checkpoint from [here](https://myshell-public-repo-hosting.s3.amazonaws.com/openvoice/checkpoints_v2_0417.zip) and extract it to the `checkpoints_v2` folder. Install [MeloTTS](https://github.com/myshell-ai/MeloTTS): ``` pip install git+https://github.com/myshell-ai/MeloTTS.git python -m unidic download ``` **Demo Usage.** Please see [`demo_part3.ipynb`](https://github.com/myshell-ai/OpenVoice/blob/main/demo_part3.ipynb) for example usage of OpenVoice V2. Now it natively supports English, Spanish, French, Chinese, Japanese and Korean. ## Install on Other Platforms This section provides the unofficial installation guides by open-source contributors in the community: - Windows - [Guide](https://github.com/Alienpups/OpenVoice/blob/main/docs/USAGE_WINDOWS.md) by [@Alienpups](https://github.com/Alienpups) - You are welcome to contribute if you have a better installation guide. We will list you here. - Docker - [Guide](https://github.com/StevenJSCF/OpenVoice/blob/update-docs/docs/DF_USAGE.md) by [@StevenJSCF](https://github.com/StevenJSCF) - You are welcome to contribute if you have a better installation guide. We will list you here. ### Links - [Github](https://github.com/myshell-ai/OpenVoice) - [HFDemo](https://huggingface.co/spaces/myshell-ai/OpenVoiceV2) - [Discord](https://discord.gg/myshell)