Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei and aishell3 datasets
| Date | Stars |
|---|---|
| 2026-07-24 | 477 |
| 2026-07-25 | 477 |
| 2026-07-28 | 477 |
| 2026-07-30 | 477 |
| 2026-07-31 | 477 |
| 2026-08-06 | 477 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Chinese mandarin text to speech (MTTS) This is a modularized Text-to-speech framework aiming to support fast research and product developments. Main features include - all modules are configurable via yaml, - speaker embedding / prosody embeding/ multi-stream text embedding are supported and configurable, - various vocoders (VocGAN, hifi-GAN, waveglow, melGAN) are supported by adapter so that comparison across different vocoders can be done easily, - durations/pitch/energy variance predictor are supported, and other variances can be added easily, - and more on the road-map. Contributions are welcome. ### Audio samples Checkout the demo here [](https://www.bilibili.com/video/BV14K4y1o7xC/) - Interesting audio samples for aishell3 added [here](./docs/samples/aishell3). - The <a href="https://ranchlai.github.io/mandarin-tts/">github page</a> also hosts some samples for [biaobei](https://www.data-baker.com/en/#/data/index/source) and [aishell3](https://www.openslr.org/93/) datasets. ## Quick start ### Install ``` git clone https://github.com/ranchlai/mandarin-tts.git cd mandarin-tts git submodule update --force --recursive --init --remote pip install -e . f ``` ### Training Two examples are provided here: [biaobei](./examples/biaobei) and [aishell3](./examples/aishell3). To train your own models, first make a copy from existing examples, then prepare the melspectrogram features using [wav2mel.py](./examples/wav2mel.py) by ``` sh cd examples python wav2mel.py -c ./aishell3/config.yaml -w <aishell3_wav_folder> -m <mel_folder> -d cpu ``` prepare the scp files necessary for training, ``` sh cd examples/aishell3 python prepare.py --wav_folder <aishell3_wav_folder> --mel_folder <mel_folder> --dst_folder ./train/ ``` This will generate scp files required by config.yaml (in the dataset/train section). You would also need to check that everything is fine in the [config file](./examples/aishell3/config.yaml). Usually you don't need to change the code. Now you can start your training by ``` sh cd examples/aishell3 python ../../mtts/train.py -c config.yaml -d cuda ``` For biaobei dataset, the workflow is the same, except that there is no speaker embedding but you can add prosody embedding. More examples will be added. Please stay. ### Synthesize #### Pretrained mtts checkpoints Currently two examples are provided, and the corresponding checkpoints/configs are summarized as follows. | dataset | checkpoint| config | | --------------- | --------------- | --------------- | | aishell3 | [link](https://zenodo.org/record/4912321#.YMN2-FMzakA) | [link](./examples/aishell3/config.yaml)| | biaobei | [link](https://zenodo.org/record/4910507#.YMN29lMzakA) | [link](./examples/biaobei/config.yaml)| #### Supported vocoders Vocoders play the role of converting melspectrograms to waveforms. They are added as submodules and will be be trained in this project. Hence you should download the checkpoints before synthesizing. In training, vocoders are not necessary, as you can monitor the training process from generated melspectrograms and also the loss curve. Current we support the following vocoders, | Vocoder | checkpoint| github | | --------------- | --------------- | --------------- | | Waveglow | [link](https://drive.google.com/file/d/1RxvxtOlzUUvUj2dAaBKgptHC6NyMqMm3/view?usp=sharing) | [link](https://github.com/ranchlai/waveglow.git)| | hifi-gan | [link](https://drive.google.com/drive/folders/1-eEYTB5Av9jNql0WGBlRoi-WH2J7bp5Y) | [link](https://github.com/ranchlai/hifi-gan) | VocGAN |[link](https://drive.google.com/file/d/1nfD84ot7o3u2tFR7YkSp2vQWVnNJ-md_/view) [link](https://zenodo.org/record/4743731/files/vctk_pretrained_model_3180.pt)|[link](https://github.com/ranchlai/VocGAN) | | MelGAN |[link](https://drive.google.com/drive/folders/1tcg7ZK-X6RYM6-rB9_-CXvS4e_qwe_Z5?usp=sharing) |[link](https://github.com/ranchlai/melgan) | All vocoders will be ready after running ```git submodule update --forc
Excerpt of 5,184 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ffa24f475cd9cab4, topic:tts, desc:text-to-speech, readme:text-to-speech
matched fp:ffa24f475cd9cab4, topic:pytorch