NViXTTS 0.0.2

Deep learning for Vietnamese Text to Speech

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