Deep learning for Vietnamese Text to Speech
Project description
NViXTTS
NViXTTS is a library for advanced Text-to-Speech generation modified based on project TTS==0.22.0
Replace for
pip install --use-deprecated=legacy-resolver -e ./TTS
from NViXTTS.tts.configs.xtts_config import XttsConfig
from NViXTTS.tts.models.xtts import Xtts
Or
from NViXTTS import XttsConfig
from NViXTTS import Xtts
Note:
I'm just a contributor by modifying the library to make it easier to use for my code, so the copyright must still follow link
Directory structure
Root path: ./NViXTTS
- .models.json
- api.py
- bin/
- collect_env_info.py
- compute_attention_masks.py
- compute_embeddings.py
- compute_statistics.py
- eval_encoder.py
- extract_tts_spectrograms.py
- find_unique_chars.py
- find_unique_phonemes.py
- remove_silence_using_vad.py
- resample.py
- synthesize.py
- train_encoder.py
- train_tts.py
- train_vocoder.py
- tune_wavegrad.py
- __init__.py
- config/
- shared_configs.py
- __init__.py
- __pycache__/
- shared_configs.cpython-310.pyc
- __init__.cpython-310.pyc
- demos/
- xtts_ft_demo/
- requirements.txt
- utils/
- formatter.py
- gpt_train.py
- xtts_demo.py
- encoder/
- configs/
- base_encoder_config.py
- emotion_encoder_config.py
- speaker_encoder_config.py
- dataset.py
- losses.py
- models/
- base_encoder.py
- lstm.py
- resnet.py
- __init__.py
- __pycache__/
- base_encoder.cpython-310.pyc
- lstm.cpython-310.pyc
- resnet.cpython-310.pyc
- README.md
- requirements.txt
- utils/
- generic_utils.py
- prepare_voxceleb.py
- training.py
- visual.py
- __init__.py
- __pycache__/
- generic_utils.cpython-310.pyc
- __init__.cpython-310.pyc
- __init__.py
- __pycache__/
- losses.cpython-310.pyc
- __init__.cpython-310.pyc
- model.py
- server/
- conf.json
- README.md
- server.py
- static/
- coqui-log-green-TTS.png
- templates/
- details.html
- index.html
- __init__.py
- tts/
- configs/
- align_tts_config.py
- bark_config.py
- delightful_tts_config.py
- fastspeech2_config.py
- fast_pitch_config.py
- fast_speech_config.py
- glow_tts_config.py
- neuralhmm_tts_config.py
- overflow_config.py
- shared_configs.py
- speedy_speech_config.py
- tacotron2_config.py
- tacotron_config.py
- tortoise_config.py
- vits_config.py
- xtts_config.py
- __init__.py
- __pycache__/
- shared_configs.cpython-310.pyc
- xtts_config.cpython-310.pyc
- __init__.cpython-310.pyc
- datasets/
- dataset.py
- formatters.py
- __init__.py
- __pycache__/
- dataset.cpython-310.pyc
- formatters.cpython-310.pyc
- __init__.cpython-310.pyc
- layers/
- align_tts/
- duration_predictor.py
- mdn.py
- __init__.py
- bark/
- hubert/
- hubert_manager.py
- kmeans_hubert.py
- tokenizer.py
- __init__.py
- inference_funcs.py
- load_model.py
- model.py
- model_fine.py
- __init__.py
- delightful_tts/
- acoustic_model.py
- conformer.py
- conv_layers.py
- encoders.py
- energy_adaptor.py
- kernel_predictor.py
- networks.py
- phoneme_prosody_predictor.py
- pitch_adaptor.py
- variance_predictor.py
- __init__.py
- feed_forward/
- decoder.py
- duration_predictor.py
- encoder.py
- __init__.py
- generic/
- aligner.py
- gated_conv.py
- normalization.py
- pos_encoding.py
- res_conv_bn.py
- time_depth_sep_conv.py
- transformer.py
- wavenet.py
- __init__.py
- glow_tts/
- decoder.py
- duration_predictor.py
- encoder.py
- glow.py
- transformer.py
- __init__.py
- losses.py
- overflow/
- common_layers.py
- decoder.py
- neural_hmm.py
- plotting_utils.py
- __init__.py
- tacotron/
- attentions.py
- capacitron_layers.py
- common_layers.py
- gst_layers.py
- tacotron.py
- tacotron2.py
- __init__.py
- tortoise/
- arch_utils.py
- audio_utils.py
- autoregressive.py
- classifier.py
- clvp.py
- diffusion.py
- diffusion_decoder.py
- dpm_solver.py
- random_latent_generator.py
- tokenizer.py
- transformer.py
- utils.py
- vocoder.py
- wav2vec_alignment.py
- xtransformers.py
- vits/
- discriminator.py
- networks.py
- stochastic_duration_predictor.py
- transforms.py
- xtts/
- dvae.py
- gpt.py
- gpt_inference.py
- hifigan_decoder.py
- latent_encoder.py
- perceiver_encoder.py
- stream_generator.py
- tokenizer.py
- trainer/
- dataset.py
- gpt_trainer.py
- xtts_manager.py
- zh_num2words.py
- __init__.py
- __pycache__/
- gpt.cpython-310.pyc
- gpt_inference.cpython-310.pyc
- hifigan_decoder.cpython-310.pyc
- latent_encoder.cpython-310.pyc
- perceiver_encoder.cpython-310.pyc
- stream_generator.cpython-310.pyc
- tokenizer.cpython-310.pyc
- xtts_manager.cpython-310.pyc
- zh_num2words.cpython-310.pyc
- __init__.py
- __pycache__/
- losses.cpython-310.pyc
- __init__.cpython-310.pyc
- models/
- align_tts.py
- bark.py
- base_tacotron.py
- base_tts.py
- delightful_tts.py
- forward_tts.py
- glow_tts.py
- neuralhmm_tts.py
- overflow.py
- tacotron.py
- tacotron2.py
- tortoise.py
- vits.py
- xtts.py
- __init__.py
- __pycache__/
- base_tts.cpython-310.pyc
- xtts.cpython-310.pyc
- __init__.cpython-310.pyc
- utils/
- assets/
- tortoise/
- tokenizer.json
- data.py
- fairseq.py
- helpers.py
- languages.py
- managers.py
- measures.py
- monotonic_align/
- core.c
- core.pyx
- setup.py
- __init__.py
- __pycache__/
- __init__.cpython-310.pyc
- speakers.py
- ssim.py
- synthesis.py
- text/
- bangla/
- phonemizer.py
- __init__.py
- belarusian/
- phonemizer.py
- __init__.py
- characters.py
- chinese_mandarin/
- numbers.py
- phonemizer.py
- pinyinToPhonemes.py
- __init__.py
- cleaners.py
- cmudict.py
- english/
- abbreviations.py
- number_norm.py
- time_norm.py
- __init__.py
- french/
- abbreviations.py
- __init__.py
- japanese/
- phonemizer.py
- __init__.py
- korean/
- korean.py
- ko_dictionary.py
- phonemizer.py
- __init__.py
- phonemizers/
- bangla_phonemizer.py
- base.py
- belarusian_phonemizer.py
- espeak_wrapper.py
- gruut_wrapper.py
- ja_jp_phonemizer.py
- ko_kr_phonemizer.py
- multi_phonemizer.py
- zh_cn_phonemizer.py
- __init__.py
- punctuation.py
- tokenizer.py
- __init__.py
- visual.py
- __init__.py
- __pycache__/
- data.cpython-310.pyc
- helpers.cpython-310.pyc
- languages.cpython-310.pyc
- managers.cpython-310.pyc
- speakers.cpython-310.pyc
- ssim.cpython-310.pyc
- synthesis.cpython-310.pyc
- visual.cpython-310.pyc
- __init__.cpython-310.pyc
- __init__.py
- __pycache__/
- __init__.cpython-310.pyc
- utils/
- audio/
- numpy_transforms.py
- processor.py
- torch_transforms.py
- __init__.py
- __pycache__/
- numpy_transforms.cpython-310.pyc
- processor.cpython-310.pyc
- torch_transforms.cpython-310.pyc
- __init__.cpython-310.pyc
- callbacks.py
- capacitron_optimizer.py
- distribute.py
- download.py
- downloaders.py
- generic_utils.py
- io.py
- manage.py
- radam.py
- samplers.py
- synthesizer.py
- training.py
- vad.py
- __init__.py
- __pycache__/
- generic_utils.cpython-310.pyc
- io.cpython-310.pyc
- __init__.cpython-310.pyc
- vc/
- configs/
- freevc_config.py
- shared_configs.py
- __init__.py
- models/
- base_vc.py
- freevc.py
- __init__.py
- modules/
- freevc/
- commons.py
- mel_processing.py
- modules.py
- speaker_encoder/
- audio.py
- hparams.py
- speaker_encoder.py
- __init__.py
- wavlm/
- config.json
- modules.py
- wavlm.py
- __init__.py
- __init__.py
- __init__.py
- VERSION
- vocoder/
- configs/
- fullband_melgan_config.py
- hifigan_config.py
- melgan_config.py
- multiband_melgan_config.py
- parallel_wavegan_config.py
- shared_configs.py
- univnet_config.py
- wavegrad_config.py
- wavernn_config.py
- __init__.py
- datasets/
- gan_dataset.py
- preprocess.py
- wavegrad_dataset.py
- wavernn_dataset.py
- __init__.py
- layers/
- hifigan.py
- losses.py
- lvc_block.py
- melgan.py
- parallel_wavegan.py
- pqmf.py
- qmf.dat
- upsample.py
- wavegrad.py
- __init__.py
- models/
- base_vocoder.py
- fullband_melgan_generator.py
- gan.py
- hifigan_discriminator.py
- hifigan_generator.py
- melgan_discriminator.py
- melgan_generator.py
- melgan_multiscale_discriminator.py
- multiband_melgan_generator.py
- parallel_wavegan_discriminator.py
- parallel_wavegan_generator.py
- random_window_discriminator.py
- univnet_discriminator.py
- univnet_generator.py
- wavegrad.py
- wavernn.py
- __init__.py
- pqmf_output.wav
- README.md
- utils/
- distribution.py
- generic_utils.py
- __init__.py
- __init__.py
- __init__.py
- __pycache__/
- model.cpython-310.pyc
- __init__.cpython-310.pyc
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Close
Hashes for NViXTTS-0.0.2-cp311-cp311-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 0596cb1b8fd983ded05bd8b10ec92efdbbed86ce6ccd5cd651375a7b8d19912a |
|
MD5 | 54e3a9f6a163c35a5b4c69cdd500a640 |
|
BLAKE2b-256 | 47cfc28ce77036e3f4e30361f258cef800a19df0758b661887356da20459f2c6 |