-
TorchBench CI has detected a performance signal or runtime regression.
Base PyTorch commit: 9a8c6559561431401ed10d063c9d28a87aaa5db2
Affected PyTorch commit: 9a8c6559561431401ed10d063c9d28a87aaa5db…
-
### Describe the bug
Try to learn the recipe in Hifigan vocoder, and something wrong like this, maybe be related to torchaudio, to my best knowledge, can't debug this. I am very appreciated for your …
-
Hi!
I trained tacotron 2 with x-vector on multi-speaker Japanese corpus, but I cannot inference by this model.
I used `espnet2.bin.tts_inference.Text2Speech` to inference.
```
File "/work/abel…
-
Hello there,
I am having this issue in the synthisiss step
Type: Exception
Text: Warning! Reached max decoder steps. Either the model is low quality or the given sentence is too short/long
Full: T…
-
I served waveglow_synthesizer and predict.
$ curl http://127.0.0.1:8080/predictions/waveglow_synthesizer -T sample_text.txt -o audio.wav
But I get the following error and cannot generate audio.
`…
-
### Describe the bug
I got an error when training multi speakers after adding a new speaker, before that I'm training a single speaker.
My train.py:
```
import os
from trainer import Train…
-
Sometimes, things don't go your way, and your already deep down the rabbit hole. Maybe you've spent 2 hours training a model, and you just realized now you want to change some config, but you have set…
-
# I want to train new model with my dataset for other language
# one case in my dataset json file is:
`{"audio_filepath": "./wav/4.wav", "duration": 5.6750625, "is_phoneme": 1, "original_text": "gAm…
-
TorchBench CI has detected a performance signal or runtime regression.
Base PyTorch commit: 1b6d6e98fed5cdb0a0c2fedd5354dd8b83dd07f1
Affected PyTorch commit: 1b6d6e98fed5cdb0a0c2fedd5354dd8b83dd07f…
-
Hi!
I try to inference using Tacotron2 with SpeechBrain x-vector.
I checked [ESPnet2-TTS realtime demonstration](https://espnet.github.io/espnet/notebook/espnet2_tts_realtime_demo.html), but that…