Feature/add phonemizer metadata #125
Open
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
…Rollback to this commit if the config file inputs dont work.
…do some comment cleanup.
cschaefer26
reviewed
Jan 20, 2022
| test_metadata_path = cm.valid_metadata_path | ||
| print(f'\nReading metadata from {metadatareader.metadata_path}') | ||
| print(f'\nFound {len(metadatareader.filenames)} lines.') | ||
| def get_short_files(phonemized=False): |
| print(f'\nReading metadata from {metadatareader.metadata_path}') | ||
| print(f'\nFound {len(metadatareader.filenames)} lines.') | ||
| def get_short_files(phonemized=False): | ||
| if not phonemized: |
There was a problem hiding this comment.
Suggested change
| if not phonemized: | |
| symbol_list = all_phonemes if phonemized else _alphabet |
| return filter_metadata | ||
|
|
||
|
|
||
| remove_files = pickle.load(open(cm.data_dir / 'under-over_sized_mels.pkl', 'rb')) |
| remove_files = pickle.load(open(cm.data_dir / 'under-over_sized_mels.pkl', 'rb')) | ||
| phonemized_metadata_path = cm.phonemized_metadata_path | ||
| train_metadata_path = cm.train_metadata_path | ||
| test_metadata_path = cm.valid_metadata_path |
There was a problem hiding this comment.
inconsistent naming of train and validation
|
|
||
| new_metadata = [f'{k}|{v}\n' for k, v in phonemized_data.items()] | ||
| shuffled_metadata = np.random.permutation(new_metadata) | ||
| train_metadata = shuffled_metadata[0:train_len] |
There was a problem hiding this comment.
Suggested change
| train_metadata = shuffled_metadata[0:train_len] | |
| train_metadata = shuffled_metadata[0:-test_len] |
There was a problem hiding this comment.
I think its safer to just use the test_len, also it saves a couple of lines
| file.writelines(test_metadata) | ||
|
|
||
| # some checks | ||
| assert metadata_len == len(set(list(phonemized_data.keys()))), \ |
There was a problem hiding this comment.
Suggested change
| assert metadata_len == len(set(list(phonemized_data.keys()))), \ | |
| assert metadata_len == len(phonemized_data) |
There was a problem hiding this comment.
Same for the other dict keys.
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.
phoneme_languageflag intraining_config.yamlskip_phonemizationflag since it was unused