Implement missing speed functions along with durable speech rate / speed changer function. #4115
+5,239
−7,588
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
Removes a (GPL) dependency
refactor(dataset): get audio length with torchaudio
refactor(bin.find_unique_chars): use existing function
Reverts c59f0ca (coqui-ai#13) Too many CI test timeouts from installing torch/nvidia packages with uv: astral-sh/uv#1912
Update repository links, package names, release script
Can be handled by adjusting logging levels instead.
Update links and Github actions
The XTTS model itself already supports Hindi, it was just in these components.
Use Python logging instead of print()
feat(xtts): support Hindi for sentence-splitting and fine-tuning
Add tokenizer logging, update version for release 0.23.0
…ids file Previously, running `LanguageManager.init_from_config(config)` would never use the `language_ids_file` if that field is present because it was overwritten in the next line with a new manager that manually parses languages from the datasets in the config. Now that is only used as a fallback.
fix(xtts): clearer error message when file given to checkpoint_dir
Expand Python API capabilities
Improve documentation
feat: allow both Path and strings where possible and add type hints
This way the outputs are available for further downstream processing, e.g. with grep. For TTS/bin/synthesize.py, if --pipe_out is set, log to stderr because then only the output audio stream should be on stdout, e.g. to pipe it to aplay.
fix(bin): log to stdout in cli tools
…ai#237) * Fix num2words call using non-standard lang code * build: update minimum num2words version --------- Co-authored-by: Enno Hermann <[email protected]>
…e durable latents. also missed tts speed implementations added.
|
|
|
Since I learned that this repo is no longer used and maintained, I am closing the mr here and opening it to idiap's repo. It continues from here. idiap#239 |
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.
Added missing speed parameters to functions and ensured more durable, accurate speed adjustments with the new
adjust_speech_ratefunction.