* Implement most similar ref training approach
* Use non-enhanced hifigan for test samples
* Add Perceiver
* Update GPT Trainer for perceiver support
* Update XTTS docs
* Bug fix masking with XTTS perceiver
* Bug fix on gpt forward
* Bug Fix on XTTS v2.0 training
* Add XTTS v2.0 unit tests
* Add XTTS v2.0 inference unit tests
* Bug Fix on diffusion inference
* Add XTTS v2.0 training recipe
* Placeholder model entry
* Add cloning params to config
* Make prompt embedding configurable
* Make cloning configurable
* Cheap fix for a cheaper fix
* Prevent resampling
* Update model entry
* Update docs
* Update requirements
* Code linting
* Add xtts v2 to sep tests
* Bug fix on XTTS get_gpt_cond_latents
* Bug fix on rebase
* Make style
* Bug fix in Japenese tokenizer
* Add num2words to deps
* Remove unused kwarg and added num_beams=1 as default
---------
Co-authored-by: Eren G??lge <egolge@coqui.ai>
* add add cli options for play and speed
--play argument uses simpleaudio to play the tts wav
--speed <float 0.0-2.0> passes speed argument to Coqui Studio models
* remove simpleaudio not referenced in file
* fix simpleaudio dependency version
* add ALSA headers for simpleaudio compilation
* Dockerfile ALSA headers for simpleaudio
* base changes to use stdout instead of play audio
Considering conversion to pipe wav data for audio playback with ohter program
like aplay.
This is incomplete code. Using to get feedback before proceeding with
implementation.
* remove play for pipe_out arg that suppresses stdout
removed play and simpleaudio dependency in place of pipe
fuctionality to allow passing wav file data to a program
dedicated to playing audio.
* scipy.io.wavfile.write fails with /dev/null target
* Streaming inference for XTTS 🚀 (#3035)
* v0.17.7
* Redownload XTTS with the local and remote config do not match
* Remove unused method
* Print a message when it is already donwloaded
* Try-except to present error when the user dont have connection
* Fix style
* 0.17.8
* v0.17.8
---------
Co-authored-by: Julian Weber <julian.weber@hotmail.fr>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
Co-authored-by: Edresson Casanova <edresson1@gmail.com>
Co-authored-by: ggoknar <ggoknar@coqui.ai>
* It looks like the Neon model is special in that t does not have a speaker_name and it wants to get the only item available. This was blocking a valid model with one speaker and a d_vector_file from being executed to get the embedding.
* Update synthesizer.py
oh my how embarrassing
commit dd612fd72e
Author: JiangCheng <jiangcheng@kezaihui.com>
Date: Mon Jun 5 16:04:54 2023 +0800
Failed to download the file and need to delete the created file path
* initial commit
* Tortoise inference
* revert path change
* style fix
* remove accidental remove
* style fixes
* style fixes
* removed unwanted assests and deps
* remove changes
* remove cvvp
* style fix black
* added tortoise config and updated config and args, refactoring the code
* added tortoise to api
* Pull mel_norm from url
* Use TTS cleaners
* Let download model files
* add ability to pass tortoise presets through coqui api
* fix tests
* fix style and tests
* fix tts commandline for tortoise
* Add config.json to tortoise
* Use kwargs
* Use regular model api for loading tortoise
* Add load from dir to synthesizer
* Fix Tortoise floats
* Use model_dir when there are multiple urls
* Use `synthesize` when exists
* lint fixes and resolve preset bug
* resolve a download bug and update model link
* fix json
* do tortoise inference from voice dir
* fix
* fix test
* fix speaker id and remove assests
* update inference_tests.yml
* replace inference_test.yml
* fix extra dir as None
* fix tests
* remove space
* Reformat docstring
* Add docs
* Update docs
* lint fixes
---------
Co-authored-by: Eren Gölge <egolge@coqui.ai>
Co-authored-by: Eren Gölge <erogol@hotmail.com>
* Warn when lang is not avail
* Make style
* Implement Coqui Studio API
* Test
* Update docs
* Set action
* Make style
* Make lint
* Update README
* Make style
* Fix action
* Run actions
* Fixed bug related to yourtts speaker embeddings issue
* Reverted code for base_tts
* Bug fix on VITS d_vector_file type
* Ignore the test speakers on YourTTS recipe
* Add speaker encoder model and config on YourTTS recipe to easily do zero-shot inference
* Update YourTTS config file
* Update ModelManager._update_path to deal with list attributes
* Fix lint checks
* Remove unused code
* Fix unit tests
* Reset name_to_id to get the right speaker ids on load_embeddings_from_list_of_files
* Set weighted_sampler_multipliers as an empty dict to prevent users' mistakes
Co-authored-by: Edresson Casanova <edresson1@gmail.com>
* Adding pretrained Overflow model
* Stabilize HMM
* Fixup model manager
* Return `audio_unique_name` by default
* Distribute max split size over datasets
* Fixup eval_split_size
* Make style
* Cache fsspec downloaded files
* Use diff paths for test
* Make fsspec caching optional
* Decom GPU docker tests
* Make progress bar optional for better CI log
* Check path local
* Update BaseDatasetConfig
- Add dataset_name
- Chane name to formatter_name
* Update compute_embedding
- Allow entering dataset by args
- Use released model by default
- Use the new key format
* Update loading
* Update recipes
* Update other dep code
* Update tests
* Fixup
* Load multiple embedding files
* Fix argument names in dep code
* Update docs
* Fix argument name
* Fix linter
- updated the recipes activating more losses for more stable training
- re-enabling guided attention loss
- fixed a bug about not the correct lr fetched for logging
* 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>
* Add upsample VITS support
* Fix the bug in inference
* Fix lint checks
* Add RMS based norm in save_wav method
* Style fix
* Add the period for VITS multi-period discriminator in model_args
* Bug fix in speaker encoder load in inference time
* Add unit tests
* Remove useless detach_z_vocoder parameter
* Add docs for VITS upsampling
* Fix the docs
* Rename TTS_part_sample_rate to encoder_sample_rate
* Add upsampling_init and upsampling_z methods
* Add asserts for encoder_sample_rate part
* Move upsampling tests to test_vits.py
* Enforce phonemizer definition for synthesis
* Fix train_tts, tokenizer init can now edit config
* Add small change to trigger CI pipeline
* fix wrong output path for one tts_test
* Fix style
* Test config overides by args and tokenizer
* Fix style
* Add support for voice conversion inference
* Cache d_vectors_by_speaker for fast inference using a bigger speakers.json
* Rebase bug fix
* Use the average d-vector for inference
Edresson Casanova
Aarni Koskela
Julian Weber
David Garvey
Dusty Hagstrom
Eren Gölge
Eren G??lge
Cohee
Jake Tae
Aleś Bułojčyk
logan hart
JiangCheng
Shukrullo Turgunov
manmay nakhashi
prakharpbuf
Matthew Boakes
Roee Shenberg
marius851000
Khalid Bashir
Victor Shepardson
p0p4k
a-froghyar