FastSpeech

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #go #android #docker #java #nodejs #vue #awesome-list #pytorch #mcp

(★ 54)

Implementation of "FastSpeech: Fast, Robust and Controllable Text to Speech"

FastSpeech 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# FastSpeech
Implementation of ["FastSpeech: Fast, Robust and Controllable Text to Speech"](https://arxiv.org/abs/1905.09263)  
  
## Training  
0. Set `data_path` in `hparams.py` as the LJSpeech folder  
1. Set `teacher_dir` in `hparams.py` as the data directory where the alignments and melspectrogram targets are saved  
2. Put checkpoint of the pre-trained transformer-tts (weights of the embedding/encoder layers are used)  
3. `python train.py`

## Training curves (orange: character  / blue: phoneme)  
##### The size of the train dataset is different because transformer-tts trained with phoneme shows more diagonal attention  
##### train:val:test=8:1:1, total => character:1126 / phoneme:3412  
<img src="figures/duration_loss.JPG" height="200">  
<img src="figures/train_loss.JPG" height="200">  
<img src="figures/val_loss.JPG" height="200">

## Training plots (orange: batch_size:64 / blue: batch_size:32)  
<img src="figures/melspec.JPG" height="300">

## Audio Samples    
You can hear the audio samples [here](https://leeyoonhyung.github.io/FastSpeech/)

FastSpeech

FastSpeech 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

FastSpeech

FastSpeech 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README