From 42499f7d38b0497066d107e68fdc358af58bb300 Mon Sep 17 00:00:00 2001 From: dengwei Date: Tue, 11 Feb 2025 12:19:19 +0800 Subject: [PATCH] init --- README.md | 166 +++++++++++------------------------------------------- 1 file changed, 32 insertions(+), 134 deletions(-) diff --git a/README.md b/README.md index 6c62495..b81adb9 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@

IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

- + ## 👉🏻 IndexTTS 👈🏻 @@ -39,131 +39,32 @@ The main improvements and contributions are summarized as follows: ## 📑 Evaluation -**Word Error Rate (WER) and Speaker Similarity (SS) Results for IndexTTS and Baseline Models** +**Word Error Rate (WER) Results for IndexTTS and Baseline Models** + + +| **Model** | **aishell1_test** | **commonvoice_20_test_zh** | **commonvoice_20_test_en** | **librispeech_test_clean** | **avg** | +|:---------------:|:-----------------:|:--------------------------:|:--------------------------:|:--------------------------:|:--------:| +| **Human** | 2.0 | 9.5 | 10.0 | 2.4 | 5.1 | +| **CosyVoice 2** | 1.8 | 9.1 | 7.3 | 4.9 | 5.9 | +| **F5TTS** | 3.9 | 11.7 | 5.4 | 7.8 | 8.2 | +| **Fishspeech** | 2.4 | 11.4 | 8.8 | 8.0 | 8.3 | +| **FireRedTTS** | 2.2 | 11.0 | 16.3 | 5.7 | 7.7 | +| **XTTS** | 3.0 | 11.4 | 7.1 | 3.5 | 6.0 | +| **IndexTTS** | **1.3** | **7.0** | **5.3** | **2.1** | **3.7** | + + +**Speaker Similarity (SS) Results for IndexTTS and Baseline Models** + +| **Model** | **aishell1_test** | **commonvoice_20_test_zh** | **commonvoice_20_test_en** | **librispeech_test_clean** | **avg** | +|:---------------:|:-----------------:|:--------------------------:|:--------------------------:|:--------------------------:|:---------:| +| **Human** | 0.846 | 0.809 | 0.820 | 0.858 | 0.836 | +| **CosyVoice 2** | **0.796** | 0.743 | 0.742 | **0.837** | **0.788** | +| **F5TTS** | 0.743 | **0.747** | 0.746 | 0.828 | 0.779 | +| **Fishspeech** | 0.488 | 0.552 | 0.622 | 0.701 | 0.612 | +| **FireRedTTS** | 0.579 | 0.593 | 0.587 | 0.698 | 0.631 | +| **XTTS** | 0.573 | 0.586 | 0.648 | 0.761 | 0.663 | +| **IndexTTS** | 0.744 | 0.742 | **0.758** | 0.823 | 0.776 | - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Modelaishell1_testcommonvoice_20_test_zhcommonvoice_20_test_enlibrispeech_test_cleanavg
CER(%)↓SS↑CER(%)↓SS↑WER(%)↓SS↑WER(%)↓SS↑CER(%)↓SS↑
Human2.0 0.8469.5 0.80910.0 0.8202.4 0.8585.1 0.836
CosyVoice 21.8 0.7969.1 0.7437.3 0.7424.9 0.8375.9 0.788
F5TTS3.9 0.74311.7 0.7475.4 0.7467.8 0.8288.2 0.779
Fishspeech2.4 0.48811.4 0.5528.8 0.6228.0 0.7018.3 0.612
FireRedTTS2.2 0.57911.0 0.59316.3 0.5875.7 0.6987.7 0.631
XTTS3.0 0.57311.4 0.5867.1 0.6483.5 0.7616.0 0.663
IndexTTS1.3 0.7447.0 0.7425.3 0.7532.1 0.8233.7 0.776
**MOS Scores for Zero-Shot Cloned Voice** @@ -183,13 +84,10 @@ The main improvements and contributions are summarized as follows: 🌟 If you find our work helpful, please leave us a star and cite our paper. ``` -@misc{deng2025indexttsindustriallevelcontrollableefficient, - title={IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System}, - author={Wei Deng and Siyi Zhou and Jingchen Shu and Jinchao Wang and Lu Wang}, - year={2025}, - eprint={2502.05512}, - archivePrefix={arXiv}, - primaryClass={cs.SD}, - url={https://arxiv.org/abs/2502.05512}, +@article{deng2025indextts, + title={IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System}, + author={Wei Deng, Siyi Zhou, Jingchen Shu, Jinchao Wang, Lu Wang}, + journal={arXiv preprint arXiv:2502.05512}, + year={2025} } -``` +``` \ No newline at end of file