research product . Other ORP type . 2020

ESPnet2 pretrained model, kan-bayashi/jsut_tts_train_conformer_fastspeech2_transformer_teacher_raw_phn_jaconv_pyopenjtalk_accent_train.loss.ave, fs=24000, lang=jp

Kan-Bayashi;
Open Access
  • Published: 24 Dec 2020
  • Publisher: Zenodo
Abstract
This model was trained by kan-bayashi using jsut/tts1 recipe in espnet. Python APISee https://github.com/espnet/espnet_model_zoo Evaluate in the recipegit clone https://github.com/espnet/espnet cd espnet git checkout 73e3fbe6b0050a401c5945d8210f8fa206c0dcc0 pip install -e . cd egs2/jsut/tts1 # Download the model file here ./run.sh --skip_data_prep false --skip_train true --download_model kan-bayashi/jsut_tts_train_conformer_fastspeech2_transformer_teacher_raw_phn_jaconv_pyopenjtalk_accent_train.loss.ave Configconfig: conf/tuning/train_conformer_fastspeech2.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/tts_train_...
Subjects
free text keywords: ESPnet, deep-learning, python, pytorch, speech-recognition, speech-synthesis, speech-translation, machine-translation
Download fromView all 2 versions
Open Access
Zenodo
Other ORP type . 2020
Provider: Datacite
Open Access
Zenodo
Other ORP type . 2020
Provider: Datacite
Any information missing or wrong?Report an Issue