Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
coqui-tts/recipes/ljspeech
History
Edresson Casanova e45227d9ff
XTTS v2.0 (#3137) 
* 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>
 		2023-11-06 14:58:18 +01:00
..
align_tts d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
delightful_tts Add Delightful-TTS implementation (#2095) 2023-07-24 13:41:26 +02:00
fast_pitch d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
fast_speech d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
fastspeech2 Fastspeech2 (#2073) 2023-01-15 22:39:22 +01:00
glow_tts d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
hifigan Make style (#1405) 2022-03-16 12:13:55 +01:00
multiband_melgan Make style (#1405) 2022-03-16 12:13:55 +01:00
neuralhmm_tts Adding neural HMM TTS Model (#2272) 2023-01-23 11:53:04 +01:00
overflow Adding OverFlow (#2183) 2022-12-12 12:44:15 +01:00
speedy_speech d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
tacotron2-Capacitron d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
tacotron2-DCA d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
tacotron2-DDC d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
univnet Make style (#1405) 2022-03-16 12:13:55 +01:00
vits_tts d-vector handling (#1945) 2022-09-13 14:10:33 +02:00
wavegrad Make style 2022-02-25 11:26:59 +01:00
wavernn Make style 2022-02-25 11:26:59 +01:00
xtts_v1 Run `make style` & re-enable it in CI (#3127) 2023-11-06 11:36:37 +01:00
xtts_v2 XTTS v2.0 (#3137) 2023-11-06 14:58:18 +01:00
README.md Create LJSpeech recipes for all the models 2021-06-22 16:21:11 +02:00
download_ljspeech.sh Update ljspeech download 2022-02-25 11:12:44 +01:00

README.md

🐸💬 TTS LJspeech Recipes

For running the recipes

  1. Download the LJSpeech dataset here either manually from its official website or using download_ljspeech.sh.

  2. Go to your desired model folder and run the training.

    Running Python files. (Choose the desired GPU ID for your run and set CUDA_VISIBLE_DEVICES)

    CUDA_VISIBLE_DEVICES="0" python train_modelX.py

    Running bash scripts.

    bash run.sh

💡 Note that these runs are just templates to help you start training your first model. They are not optimized for the best result. Double-check the configurations and feel free to share your experiments to find better parameters together 💪.