mirror of https://github.com/coqui-ai/TTS.git
8be21ec387
* new CI config * initial Capacitron implementation * delete old unused file * fix empty formatting changes * update losses and training script * fix previous commit * fix commit * Add Capacitron test and first round of test fixes * revert formatter change * add changes to the synthesizer * add stepwise gradual lr scheduler and changes to the recipe * add inference script for dev use * feat: add posterior inference arguments to synth methods - added reference wav and text args for posterior inference - some formatting * fix: add espeak flag to base_tts and dataset APIs - use_espeak_phonemes flag was not implemented in those APIs - espeak is now able to be utilised for phoneme generation - necessary phonemizer for the Capacitron model * chore: update training script and style - training script includes the espeak flag and other hyperparams - made style * chore: fix linting * feat: add Tacotron 2 support * leftover from dev * chore:rename parser args * feat: extract optimizers - created a separate optimizer class to merge the two optimizers * chore: revert arbitrary trainer changes * fmt: revert formatting bug * formatting again * formatting fixed * fix: log func * fix: update optimizer - Implemented load_state_dict for continuing training * fix: clean optimizer init for standard models * improvement: purge espeak flags and add training scripts * Delete capacitronT2.py delete old training script, new one is pushed * feat: capacitron trainer methods - extracted capacitron specific training operations from the trainer into custom methods in taco1 and taco2 models * chore: renaming and merging capacitron and gst style args * fix: bug fixes from the previous commit * fix: implement state_dict method on CapacitronOptimizer * fix: call method * fix: inference naming * Delete train_capacitron.py * fix: synthesize * feat: update tests * chore: fix style * Delete capacitron_inference.py * fix: fix train tts t2 capacitron tests * fix: double forward in T2 train step * fix: double forward in T1 train step * fix: run make style * fix: remove unused import * fix: test for T1 capacitron * fix: make lint * feat: add blizzard2013 recipes * make style * fix: update recipes * chore: make style * Plot test sentences in Tacotron * chore: make style and fix import * fix: call forward first before problematic floordiv op * fix: update recipes * feat: add min_audio_len to recipes * aux_input["style_mel"] * chore: make style * Make capacitron T2 recipe more stable * Remove T1 capacitron Ljspeech * feat: implement new grad clipping routine and update configs * make style * Add pretrained checkpoints * Add default vocoder * Change trainer package * Fix grad clip issue for tacotron * Fix scheduler issue with tacotron Co-authored-by: Eren Gölge <egolge@coqui.ai> Co-authored-by: WeberJulian <julian.weber@hotmail.fr> Co-authored-by: Eren Gölge <erogol@hotmail.com> |
||
|---|---|---|
| .. | ||
| tacotron1-Capacitron | ||
| tacotron2-Capacitron | ||
| README.md | ||
README.md
How to get the Blizzard 2013 Dataset
The Capacitron model is a variational encoder extension of standard Tacotron based models to model prosody.
To take full advantage of the model, it is advised to train the model with a dataset that contains a significant amount of prosodic information in the utterances. A tested candidate for such applications is the blizzard2013 dataset from the Blizzard Challenge, containing many hours of high quality audio book recordings.
To get a license and download link for this dataset, you need to visit the website of the Centre for Speech Technology Research of the University of Edinburgh.
You get access to the raw dataset in a couple of days. There are a few preprocessing steps you need to do to be able to use the high fidelity dataset.