-
I have two question：
1.when process baker dataset, in get_phoneme_from_char_and_pinyin function, 'sil' is added in result, but in preprocess.py gen_audio_features function, trim_silence parameter is …
-
Support Chinese stt?
-
## 🐛 Bug
I'm trying to export Mozilla TTS Tacotron2 model into ONNX using TorchScript.
Here is my current progress: https://github.com/lasa01/TTS/tree/onnx.
Here is the export script: https:/…
-
先日はissuesに反応してくださりありがとうございます。
今回の質問は主にp332の内容です。新しく音声合成を作ろうと思ったのですが、コーパスの規模がJSUTコーパスよりも小さいため転移学習をしようと考えました。
しかし出力されたチェックポイントを初期値として学習させる方法が分からず質問させていただきました。
ご存知かとは思いますが、NVIDIA/tacotron2では学習スクリプトを実行…
-
Greetings!
I've tried to replace your supplied pretrained ParallelWaveGAN checkpoint with a different one I trained (Using the implementation over at https://github.com/kan-bayashi/ParallelWaveGAN …
-
First of all, thanks guys for your great work and support.
I have some problem with flowtron.
Especially, the model repeating itself. And provide only 4sec sentence.
Even if sentence has 1 sec. S…
-
**Describe the bug**
I installed TTS 0.4.1 and ran
tts --model_name tts_models/en/vctk/fast_pitch --text "hello world." --speaker_idx VCTK_p225
It uses vocoder_models/en/vctk/hifigan_v2 by default…
-
Please, I want to know if there is a pre-trained model in the Sapnish or German language. I was creating an implementation but I need this two languages for make it more accessible in my country. In o…
-
hello,
I went trough all the recipes and was looking for how transfer learning could be done in a similar way as described here
[transfer learning](https://github.com/NVIDIA/tacotron2/issues/223…
-
Requirement already satisfied: argcomplete>=1.8.1 in ./tools/venv/lib/python3.7/site-packages (from yq->paddle-speech==2.1.2) (1.12.3)
Building wheels for collected packages: paddle-speech
Buildin…