-
Tacotron team has released Parallel Tacotron 2, with novel duration modelling technique.
```
This section introduces the proposed Parallel Tacotron 2 model,
specifically differentiable duration mod…
-
Hi, I am not that experienced in TTS, so I've faced many problem before get the code running with my non-English dataset which has about 10k sentences (~26h long) . However, still some issues and que…
-
### Discussed in https://github.com/coqui-ai/TTS/discussions/1208
Originally posted by **DesiKeki** February 7, 2022
Hello TTS Community,
I am trying to fine tune tts_models--en--ljspeech-…
-
In the current setup when I type
```
tensorboard --logdir
```
i can visualize model training progress.
Can i also generate tensorboard graphs?
It will help me understand the architecture of …
-
I'm trying to improve French Tacotron2 DDC, because there is some noises you don't have in English synthesizer made with Tacotron 2. There is also some pronunciation defaults on nasal fricatives, cert…
-
Hi, really want coqui-tts can have a mandrain model, there also some popular data can be used to train, like Biaobei baker dataset.
-
Why not substituting the current models with later versions one?
Both Tacotron2 and Waveglow are implemented in pytorch.
-
Hi, thanks for the great work .
Is is possible to add support for the NVIDIA TensorRT library, or the official PyTorch TensorRT library, as I have read it is suppose to be easy to implement and would…
-
Thanks for your public repo, I have a question: I trained some models for TTS task like tacotron2, fastspeech, hifigan... and it's almost use mel-spectrogram from wav with sr=22050Hz, so i wonder that…
-
As the GlowTTS MAS definition:
to satisfy monotonicity and surjection, if **z_j** and …