在线时间:8:00-16:00
迪恩网络APP
随时随地掌握行业动态
扫描二维码
关注迪恩网络微信公众号
开源软件名称:syoyo/tacotron-tts-cpp开源软件地址:https://github.com/syoyo/tacotron-tts-cpp开源编程语言:C++ 77.8%开源软件介绍:Text-to-speech in (partially) C++ using Tacotron model + TensorflowRunning Tacotron model in TensorFlow C++ API. Its good for running TTS in mobile or embedded device. Code is based on keithito's tacotron implementation: https://github.com/keithito/tacotron StatusExperimental. Python preprocessing is required to generate sequence data from a text. Requirment
Dump graph.In keithito's tacotron repo, append
Freeze graphFreeze graph for example:
Example freeze graph file is included in this repo. BuildEdit libtensorflow_cc.so path(Assume you build TensorFlow from source code) in
Note on libtensorflow_ccPlease make sure building libtensorflow_cc with https://www.tensorflow.org/install/source#preconfigured_configurations RunPrepare sequence JSON file.
Sequence can be generated by using See Then,
example output01.wav and processed01.wav is included in Optional parameterYou can specify hyperparameter settings(JSON format) using
PerformanceCurrently TensorFlow C++ code path only uses single CPU core, so its slow. Time for synthesis is roughly 10x slower on 2018's CPU than synthesized audio length(e.g. 60 secs for 6 secs audio). TODO
LicenseMIT license. Pretrained model used for freezing graph is obtained from keithito's repo. Third party licenses
|
2023-10-27
2022-08-15
2022-08-17
2022-09-23
2022-08-13
请发表评论