Skip to content

Drop support for some old features and behaviors #172

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
Merged
yqzhishen merged 16 commits into from
Feb 25, 2024
Merged

Drop support for some old features and behaviors #172

yqzhishen merged 16 commits into from
Feb 25, 2024

Conversation

@yqzhishen
Copy link
Member

@yqzhishen yqzhishen commented Feb 23, 2024 •
edited
Loading

Removed features and behaviors

  • Discrete F0 embedding type (temporarily reserved in ONNX exporter)
  • Code backup on training start
  • Random seeding during training
  • Linear domain of random time stretching augmentation
  • Migration script and guidance for transcriptions and checkpoints from version 1.X.

Other changes

  • interp_uv configuration is removed and forced to True.
  • train_set_name and valid_set_name are removed and forced to train and valid.
  • num_pad_tokens is removed and forced to 1.
  • ffn_padding is removed and forced to SAME.
  • g2p_dictionary configuration is removed in favor of dictionary.
  • pndm_speedup configuration is renamed to diff_speedup.
  • The duplicate txt_embed layer in FastSpeech2 encoder is removed.
  • Some configuration keys are now directly accessed so the configuration must contain them: dictionary, diff_accelerator, f0_embed_type, pe, pndm_speedup, use_key_shift_embed, use_speed_embed.

@yqzhishen
Drop support for discrete F0 embedding (reserved in ONNX exporter)
d742758
@yqzhishen
Drop support for interp_uv configuration key
9505b54
@yqzhishen
Drop support for train_set_name and valid_set_name configuration …
c56f3f3 
…keys
@yqzhishen
Drop support for linear domain of random time stretching augmentation
9f79b75
@yqzhishen
Drop support for num_pad_tokens configuration key
9967867
@yqzhishen
Drop support for code backup before training
a09221e
@yqzhishen
Drop support for ffn_padding configuration key
bae5779
@yqzhishen
Drop support for random seeding
2045939
@yqzhishen
Add placeholder to load old checkpoint
1d2a9e8
@yqzhishen
Remove duplicate txt_embed layer (resuming may raise errors)
26e8f07
@yqzhishen
Remove migration script and error message for transcriptions.txt
49c2360
@yqzhishen
Remove seed from batch shuffling
1bc60dd
@yqzhishen
Merge remote-tracking branch 'origin/main' into drop-supports
da97762 
# Conflicts:
#	augmentation/spec_stretch.py
#	preprocessing/acoustic_binarizer.py
@yqzhishen
Use direct access on some hparam keys
969e313
@yqzhishen yqzhishen marked this pull request as ready for review February 23, 2024 17:45
@yqzhishen yqzhishen marked this pull request as draft February 23, 2024 17:45
@yqzhishen yqzhishen marked this pull request as ready for review February 25, 2024 07:48
@yqzhishen yqzhishen merged commit c16095b into openvpi:main Feb 25, 2024
agentasteriski added a commit to agentasteriski/DiffSinger_colab_notebook_MLo7 that referenced this pull request Feb 27, 2024
@agentasteriski
Remove discrete f0 embed, etc.
3de3dc4 
No longer supported as of openvpi/DiffSinger#172
Raised config f0_max to 1600 to match existing binarizer edit
use_melody_encoder now enables along with predict_pitch
@agentasteriski agentasteriski mentioned this pull request Feb 27, 2024
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@yqzhishen