This collection contains end-to-end neural models for Text to Speech (TTS) to be used with Jarvis. The models in this collection can be used for synthesizing speech from text. The current TTS pipeline requires two models. One that converts text to a spectrogram and one that converts a spectrogram to audio.
For instructions on how to use a model, please see its corresponding model card page. Please note both models are required to run the TTS pipeline. The available models can be used to generate a female English voice with an American accent. To generate a new voice, please train Tacotron 2 on a new voice. Refer to the following NeMo notebook for further information on training Tacotron 2.
By downloading and using the models and resources packaged with TLT Conversational AI, you would be accepting the terms of the Jarvis license
NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.