-
Hi, I'm working on your project and I have already did the training for 0013 voice in ESD in fine-tune (300 epochs = checkpoint_10000) and try the inference for it but the result of the convert Neutra…
-
Thank you for your contribution on the vocoder. I train the pwg and hifigan on my dataset, pwg works well however the hifigan have problem.
```
File "/home/bme2/miniconda3/envs/silent/bin/paral…
-
代码段：
with paddle.no_grad():
print('speedyspeech_inference begin', datetime.datetime.now())
mel = speedyspeech_inference(part_phone_ids, part_tone_ids)
print('pwg_inference begin', datetime.datetim…
-
Hi, I tried to train the Parallel WaveGAN on the LibriTTS dataset but confronted some issues.
I wanted to use a sampling rate of 16000 instead of 24000. However, when I tried to use a sampling rate o…
-
Using own dataset for training multiband melgan.
when running
```sh
./run.sh --conf conf/multi_band_melgan.v2.yaml --stage 1
```
I get this error:
```
(venv) ubuntu@tts-server-base-gpu-2:~/pro…
-
我自己按照csmsc格式搜集整理的语料来训练FastSpecch2+Parallel WaveGAN模型 FastSpecch2已完成153000步训练 请问Parallel WaveGAN至少需要训练到多少步 教程里要训练到400000步 目的是为了快速验证自己搜集的语料能否训练成功
-
I try to infer spectrogram which was yielded from NeMo glow_tts models
(and Vocoder model is using pre-trained models jsut_multi_band_melgan.v2 or just_hifigan.v1 )
But blow error was happened
…
-
Even thou the configs of this french model and the german are nearly the same
and both define the 'model_type' the german one leads to an error:
*working*:
https://huggingface.co/tensorspeech/tt…
-
Dear professor:
Thank you for your carefully guidence and I have successfully run the parallelwavegan.However,the distributed in config.yml is false and I want to modify it to true,can you tell me ho…
-
I'm interested in using TTS for voice synthesis for reading text.
Maybe I can't find my way around here, but the readme gives a clear and concise way to get the tool for using this text-to-speech l…