-
### Describe the bug
tts --text "autobus" --model_name tts_models/fr/mai/tacotron2-DDC --out_path speech.wav
> tts_models/fr/mai/tacotron2-DDC is already downloaded.
> vocoder_models/universal/li…
-
I'm working on Tacotron 2
I've tried to continue training from provided checkpoints ```JoC_Tacotron2_FP32_PyT_20190306``` and ```JoC_WaveGlow_FP32_PyT_20190306```, but it didn't work out.
```
::…
-
### 고민해야할 점: 테스트 데이터를 어떻게 생성할 것인가?
현재 모델 학습 시 item embedding, position embedding, type embedding을 진행
그러나 테스트 데이터를 생성할 때에는 `session_type`형태로 추천을 생성해줘야 함
따라서 각 `type`별로 추천을 만들어주기 위해 context 구성을 바꿔볼 필…
-
This is an umbrella issue to track progress and discuss priority items. Comments and requests are always welcome.
## MIlestones
- [x] ~ 4/26 (Sun): Refactor my jupyter-based code to python scrip…
-
### News
- Conferences
- ICDM 2022 (11.28 - 12. 1, Orlando, US) Notification: 모두 축하드립니다.
- EMNLP 2022: Rebuttal 1주 연장 (9.4 AoE 까지)
- AI Rush Conference 2022 (9.7 오후 1시부터)
- [디지털플랫폼정부위원회 출범]…
-
大佬您好，我最近在用tacotron2训练命运石之门中助手的语音模型，然后想用您写的软件转换成语音输出，可是在运行过程中产生了如下报错
然后我又下载了您提供的Atri的文件试着跑了一遍，发现也产生了同样的报错
请问如何解决这种情况呢？
报错如下：
Exception in Tkinter callback
Traceback (most recent call last):
…
-
I am trying to serve the model from the [NCRFpp](https://github.com/jiesutd/NCRFpp) project using torchserve. The files that are required by my custom _handler.py_ file are in multiple folders and hav…
-
We trained Tacotron2 + waveglow on a GTX 980 (4GB). However we needed to adjust some parameters in order to make it possible to run on this weak GPU - finally the training ran with following parameter…
-
### Describe the bug
I had training tacotron 2 for a while and now I want to add sample audio for one speaker. When I run using
```
CUDA_VISIBLE_DEVICES=0 python train.py --continue_path /media/…
-
Great work, thanks.