Comprehensive-E2E-TTS - PyTorch Implementation
A Non-Autoregressive End-to-End Text-to-Speech (generating waveform given text), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS. Any suggestions toward the best End-to-End TTS are welcome :)
- WavThruVec: Latent speech representation as intermediate features for neural speech synthesis (Siuzdak et al., 2022)
- JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech (Lim et al., 2022)
- FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (Ren et al., 2020)
- HiFi++: a Unified Framework for Neural Vocoding, Bandwidth Extension and Speech Enhancement (Andreev et al., 2022)
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis (Kong et al., 2020)
- Differentiable Duration Modeling for End-to-End Text-to-Speech (Nguyen et al., 2022)
- One TTS Alignment To Rule Them All (Badlani et al., 2021)
DATASET refers to the names of datasets such as
VCTK in the following documents.
You can install the Python dependencies with
pip3 install -r requirements.txt
Dockerfile is provided for
You have to download the pretrained models (will be shared soon) and put them in
For a single-speaker TTS, run
python3 synthesize.py --text "YOUR_DESIRED_TEXT" --restore_step RESTORE_STEP --mode single --dataset DATASET
For a multi-speaker TTS, run
python3 synthesize.py --text "YOUR_DESIRED_TEXT" --speaker_id SPEAKER_ID --restore_step RESTORE_STEP --mode single --dataset DATASET
The dictionary of learned speakers can be found at
preprocessed_data/DATASET/speakers.json, and the generated utterances will be put in
Batch inference is also supported, try
python3 synthesize.py --source preprocessed_data/DATASET/val.txt --restore_step RESTORE_STEP --mode batch --dataset DATASET
to synthesize all utterances in
The pitch/volume/speaking rate of the synthesized utterances can be controlled by specifying the desired pitch/energy/duration ratios. For example, one can increase the speaking rate by 20 % and decrease the volume by 20 % by
python3 synthesize.py --text "YOUR_DESIRED_TEXT" --restore_step RESTORE_STEP --mode single --dataset DATASET --duration_control 0.8 --energy_control 0.8
Add --speaker_id SPEAKER_ID for a multi-speaker TTS.
The supported datasets are
- LJSpeech: a single-speaker English dataset consists of 13100 short audio clips of a female speaker reading passages from 7 non-fiction books, approximately 24 hours in total.
- VCTK: The CSTR VCTK Corpus includes speech data uttered by 110 English speakers (multi-speaker TTS) with various accents. Each speaker reads out about 400 sentences, which were selected from a newspaper, the rainbow passage and an elicitation paragraph used for the speech accent archive.
Any of both single-speaker TTS dataset (e.g., Blizzard Challenge 2013) and multi-speaker TTS dataset (e.g., LibriTTS) can be added following LJSpeech and VCTK, respectively. Moreover, your own language and dataset can be adapted following here.
- For a multi-speaker TTS with external speaker embedder, download ResCNN Softmax+Triplet pretrained model of philipperemy's DeepSpeaker for the speaker embedding and locate it in
- Run the preprocessing script by
python3 preprocess.py --dataset DATASET
Train your model with
python3 train.py --dataset DATASET
- The trainer assumes single-node multi-GPU training. To use specific GPUs, specify
CUDA_VISIBLE_DEVICES=at the beginning of the above command.
tensorboard --logdir output/log
to serve TensorBoard on your localhost.
- Two options for embedding for the multi-speaker TTS setting: training speaker embedder from scratch or using a pre-trained philipperemy's DeepSpeaker model (as STYLER did). You can toggle it by setting the config (between
- DeepSpeaker on VCTK dataset shows clear identification among speakers. The following figure shows the T-SNE plot of extracted speaker embedding.
Please cite this repository by the "Cite this repository" of About section (top right of the main page).