Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add suppport for Thai #117

Open
wants to merge 29 commits into
base: main
Choose a base branch
from
Open

Add suppport for Thai #117

wants to merge 29 commits into from

Commits on Apr 29, 2024

  1. Add suppport for Thai

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    ffd8f41 View commit details
    Browse the repository at this point in the history

  2. Add Thai Wiktionary Corpus

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    c960e81 View commit details
    Browse the repository at this point in the history

  3. Fix issues with g2p function

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    80460cc View commit details
    Browse the repository at this point in the history

  4. Add better test cases

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    4d1fd9c View commit details
    Browse the repository at this point in the history

  5. Remove debug line

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    6d7f2ac View commit details
    Browse the repository at this point in the history

  6. More fixes

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    aff4b04 View commit details
    Browse the repository at this point in the history

  7. Fix normalize and dictionary

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    5cd7da1 View commit details
    Browse the repository at this point in the history

  8. Update expected format of test_word_tokenize test case

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 29, 2024
    Configuration menu
    Copy the full SHA
    4484651 View commit details
    Browse the repository at this point in the history

Commits on Apr 30, 2024

  1. Fix format of test_thai_text_to_phonemes test case

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 30, 2024
    Configuration menu
    Copy the full SHA
    17cafba View commit details
    Browse the repository at this point in the history

  2. Add test to compare with Korean

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 30, 2024
    Configuration menu
    Copy the full SHA
    1c74eb7 View commit details
    Browse the repository at this point in the history

  3. Clean up import statements

    Jim Eric Skogman authored and Jim Eric Skogman committed Apr 30, 2024
    Configuration menu
    Copy the full SHA
    11c5a75 View commit details
    Browse the repository at this point in the history

Commits on May 8, 2024

  1. Add missing code for training Thai language and Thai Grapheme to Phon… 

    …eme corpus file
    Jim Eric Skogman authored and Jim Eric Skogman committed May 8, 2024
    Configuration menu
    Copy the full SHA
    d8a5e13 View commit details
    Browse the repository at this point in the history

Commits on May 9, 2024

  1. Initialize the TextEncoder with fixed size

    Jim Eric Skogman authored and Jim Eric Skogman committed May 9, 2024
    Configuration menu
    Copy the full SHA
    28dd03e View commit details
    Browse the repository at this point in the history

  2. Add get_resized_embeddings to SynthesizerTrn class

    Jim Eric Skogman authored and Jim Eric Skogman committed May 9, 2024
    Configuration menu
    Copy the full SHA
    809a043 View commit details
    Browse the repository at this point in the history

  3. Use self.enc_p.emb

    Jim Eric Skogman authored and Jim Eric Skogman committed May 9, 2024
    Configuration menu
    Copy the full SHA
    818e4b4 View commit details
    Browse the repository at this point in the history

  4. Remove th_symbols from sorted list

    Jim Eric Skogman authored and Jim Eric Skogman committed May 9, 2024
    Configuration menu
    Copy the full SHA
    b25a99d View commit details
    Browse the repository at this point in the history

Commits on May 10, 2024

  1. Fix unsupported characters in g2p function

    Jim Eric Skogman authored and Jim Eric Skogman committed May 10, 2024
    Configuration menu
    Copy the full SHA
    11c55ef View commit details
    Browse the repository at this point in the history

Commits on May 16, 2024

  1. Fix tones list from g2p function being initliazed to zeroes and adjus… 

    …t test case
    Jim Eric Skogman authored and Jim Eric Skogman committed May 16, 2024
    Configuration menu
    Copy the full SHA
    3004182 View commit details
    Browse the repository at this point in the history

  2. Assign multiple phones based on the number of phones

    Jim Eric Skogman authored and Jim Eric Skogman committed May 16, 2024
    Configuration menu
    Copy the full SHA
    5b1faee View commit details
    Browse the repository at this point in the history

  3. Fix regression

    Jim Eric Skogman authored and Jim Eric Skogman committed May 16, 2024
    Configuration menu
    Copy the full SHA
    c1870d9 View commit details
    Browse the repository at this point in the history

Commits on May 18, 2024

  1. Fix tones mapping

    Jim Eric Skogman authored and Jim Eric Skogman committed May 18, 2024
    Configuration menu
    Copy the full SHA
    adb9232 View commit details
    Browse the repository at this point in the history

  2. Add new test case

    Jim Eric Skogman authored and Jim Eric Skogman committed May 18, 2024
    Configuration menu
    Copy the full SHA
    17a3bd7 View commit details
    Browse the repository at this point in the history

Commits on May 19, 2024

  1. Change format of word2ph to inlclude count

    Jim Eric Skogman authored and Jim Eric Skogman committed May 19, 2024
    Configuration menu
    Copy the full SHA
    5c19c03 View commit details
    Browse the repository at this point in the history

Commits on May 20, 2024

  1. Keep special characters in word2ph to be consistent with other languages

    Jim Eric Skogman authored and Jim Eric Skogman committed May 20, 2024
    Configuration menu
    Copy the full SHA
    a65cc2f View commit details
    Browse the repository at this point in the history

  2. Update test case for Thai bert to match format without special cases

    Jim Eric Skogman authored and Jim Eric Skogman committed May 20, 2024
    Configuration menu
    Copy the full SHA
    af38d49 View commit details
    Browse the repository at this point in the history

Commits on May 28, 2024

  1. Fix dictionary lookup and use bert tokenizer in g2p

    Jim Eric Skogman authored and Jim Eric Skogman committed May 28, 2024
    Configuration menu
    Copy the full SHA
    2be87f2 View commit details
    Browse the repository at this point in the history

  2. Fix tone issues and add warning for mismatch due to _ underscore char… 

    …acter
    Jim Eric Skogman authored and Jim Eric Skogman committed May 28, 2024
    Configuration menu
    Copy the full SHA
    120bcfd View commit details
    Browse the repository at this point in the history

  3. Squash 2 nasty bugs: 1.) Assign tone value to each phoneme excluding … 

    …the tone marker only if there is one and Keep only non-empty groups for cases with a trailing dot
    Jim Eric Skogman authored and Jim Eric Skogman committed May 28, 2024
    Configuration menu
    Copy the full SHA
    1251906 View commit details
    Browse the repository at this point in the history

Commits on Jun 5, 2024

  1. Add gradient clipping, process underscores to align with bert feature… 

    …s, add additional symbols from error during training and update tones
    Jim Eric Skogman authored and Jim Eric Skogman committed Jun 5, 2024
    Configuration menu
    Copy the full SHA
    d4c9124 View commit details
    Browse the repository at this point in the history