SpeechT5 VS NeMo

Hey! I’m doing a somewhat similar project but for TTS / voice cloning. This might not be too relevant for you but it might be one way to solve your problem. We based our project onSpeecht5 which is a multimodal setup that can take in audio or text and output audio or text. It uses speaker embeddings to handle multiple speakers, so you could use Metas S2ST to translate audio and this model to preserve the voice by doing audio to audio speech conversion. Here’s a hugging tutorial which mentions speech conversion with speecht5 https://huggingface.co/blog/speecht5

The idea to separate text from speech is important. Models released today: https://github.com/microsoft/SpeechT5/tree/main/SpeechUT SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training

I don't test WaveRNN but from the ones that I know the best that is open source is FastPitch. And it's easy to use, here is the tutorial for voice cloning.

Nowadays... bigger repos like https://github.com/NVIDIA/NeMo are all pytorch, lots of work also published by Meta and Microsoft is all torch. I check new work on GitHub all the time and I haven't seen a Tensorflow repo in years except one.

- https://github.com/NVIDIA/NeMo

Can’t you use the NeMo model and just strip the punctuation from the output again if you don’t want it? You can also fine tune the the model with capitalization only if you look at the examples https://github.com/NVIDIA/NeMo/blob/stable/tutorials/nlp/Punctuation_and_Capitalization.ipynb The capitalization and punctuation are annotated separately (U indicates that the word should be upper cased, and O - no capitalization ). The model seems to be a token level classifier not seq to seq so there should also be a way to get just the capitalization part but you would have to look into the model as it’s not shown in the examples.

I think there's been talk to do speaker diarization with whisper-asr-webservice[0] which is also written in python and should be able to make use of goodies such as pyannote-audio, py-webrtcvad, etc.

Whisper is great but at the point we get to kludging various things together it starts to make more sense to use something like Nvidia NeMo[1] which was built with all of this in mind and more

[0] - https://github.com/ahmetoner/whisper-asr-webservice

[1] - https://github.com/NVIDIA/NeMo

[커먼보이스 전자우편](mailto:[email protected]) || Common Voice || Korean Language Homepage || FAQs || Speaking Aloud and Reviewing Recordings || Sentence Collector || NVidia/NeMo

The final security grain was added with speech-to-text anti-spoofing built on QuartzNet from the Nemo framework. This model provides a decent quality user experience and is suitable for real-time scenarios. To measure how close what the person says to what the system expects, requires calculation of the Levenshtein distance between them.