Adding neural HMM TTS #2271
Closed
Adding neural HMM TTS #2271
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
… and can be dumped as json
* Draft implementation * Fix style * Add api tests * Fix lint * Update docs * Update tests * Set env * Fixup * Fixup * Fix lint * Revert
quick fix for coqui-ai#2156. added 'root_path' key.
* Add YourTTS VCTK recipe * Fix lint * Add compute_embeddings and resample_files functions to be able to reuse it * Add automatic download and speaker embedding computation for YourTTS VCTK recipe * Add parameter for eval metadata file on compute embeddings function
* 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
* Update overflow config * Pulling shuffle and drop_last from config * Print training stats for overflow
shivammehta25
commented
Jan 9, 2023
shivammehta25
commented
Jan 9, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Neural HMM TTS (2021) is a parameter-efficient version of OverFlow, it was the probabilistic spectrogram generation model which introduced neural HMMs into a TTS architecture in "Neural HMMs are all you need (for high-quality attention-free TTS)". Because of half the number of parameters the synthesis output quality is suboptimal (but comparable to Tacotron2 without Postnet) but it learns to speak with a lesser amount of data and is significantly faster than other attention-based methods.