Natooz MidiTok issues - Githubissues

Natooz / MidiTok

MIDI / symbolic music tokenizers for Deep Learning models 🎶

https://miditok.readthedocs.io/

MIT License

665 stars 81 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Using --dist worksteal for tests distribution among workers

#201 Natooz closed 6 days ago
0
Trailing Bars are not appended into REMI token sequence if last note is multibar length

#200 Mintas opened 6 days ago
1
fix import HfHubHTTPError with latest hf hub package update

#199 Natooz closed 1 week ago
0
KeyError in collators.py line 164

#198 kroll-software opened 1 week ago
1
KeyError in midi_tokenizer.py line 1712

#197 kroll-software opened 1 week ago
3
Using pitch bend in Octuple tokenizer

#196 Neptune-S-777 closed 3 weeks ago
2
split_files_for_training() throws error: pyvec::index out of range: -1

#195 kroll-software closed 1 week ago
5
collator now handles decoder input ids (seq2seq models)

#194 Natooz closed 2 months ago
0
`use_velocities` and `use_duration` configuration parameters

#193 Natooz closed 2 months ago
0
Fixing bugs caused by changes from symusic v0.5.0

#192 Natooz closed 2 months ago
0
PerTok Tokenizer

#191 JLenzy closed 3 weeks ago
3
Environment Issue (Nanobind Error)

#190 MHZ9825 closed 1 month ago
6
REMI with rests does not produce Bar tokens if rest is at the end of a bar

#189 mister-magpie closed 1 month ago
4
Bump actions/upload-artifact from 3 to 4

#188 dependabot[bot] closed 2 months ago
0
Bump codecov/codecov-action from 3.1.0 to 4.5.0

#187 dependabot[bot] closed 2 months ago
0
Bump actions/download-artifact from 3 to 4

#186 dependabot[bot] closed 2 months ago
0
Bump actions/stale from 5.1.1 to 9.0.0

#185 dependabot[bot] closed 2 months ago
0
rST Documentation fixes

#184 scottclowe closed 3 months ago
1
making sure MMM token sequences are not concatenated when splitting them per bar/beat in tokenizer_training_iterator.py

#183 Natooz closed 3 months ago
0
better distinction between `one_token_stream` and `config.one_token_stream_for_programs`

#182 Natooz closed 3 months ago
0
Attribute controls feature

#181 helloWorld199 closed 3 months ago
1
Logo now with white outer stroke

#180 Natooz closed 3 months ago
1
How to choose the vocab_size for training a bpe tokenizer?

#179 paranoid2droid closed 3 months ago
4
Cannot install it

#178 shawn120 closed 3 months ago
6
Fixing split methods for empty files (no tracks and/or no notes)

#177 Natooz closed 4 months ago
0
Handling Incompatible Files During `split_files_for_training`

#176 Kinyugo closed 4 months ago
20
Docs update

#175 Natooz closed 4 months ago
1
Dration token meaning in REMI

#174 PRamoneda closed 2 months ago
5
`TokSequence` summable, `concatenate_track_sequences` arg for MMM

#173 Natooz closed 4 months ago
1
adding `no_preprocess_score` argument when tokenizing

#172 Natooz closed 4 months ago
0
Defining Custom Tokens

#171 MikeMpapa closed 3 months ago
3
small bug fix in MIDI pretokenization

#170 shenranwang closed 4 months ago
0
Structured tokenizer order is different from documentation

#169 mister-magpie closed 2 months ago
3
Default `continuing_subword_prefix` when splitting token sequences

#168 Natooz closed 4 months ago
1
Fixing docs for tokenizer training

#167 Natooz closed 4 months ago
0
after tokenizing with trained tokenizer, the "tokens" array contains original tokens

#166 theglassofwater closed 2 months ago
5
`_model_name` is now a protected property

#165 Natooz closed 4 months ago
0
updates to Example_HuggingFace_Mistral_Transformer.ipynb

#164 briane412 closed 5 months ago
0
The Example_HuggingFace_Mistral_Transformer.ipynb notebook gives a ValueError when running trainer.train()

#163 briane412 closed 4 months ago
5
Support for abc files

#162 Natooz closed 5 months ago
0
`tokenizer.train` supporting Unigram and WordPiece

#161 Natooz closed 5 months ago
1
Minor improvements and function name changes

#160 Natooz closed 5 months ago
1
Error in training tokenizer "UnicodeDecodeError: 'utf-8' codec can't decode byte 0xf0 in position 0: invalid continuation byte"

#159 ojus1 closed 4 months ago
16
cannot import DatasetTok - Error with version 3.0.2

#158 seb-son closed 6 months ago
3
Error running the 2nd example in readme

#157 MikeMpapa closed 6 months ago
12
MMM refactor

#156 Natooz closed 6 months ago
1
Installation Error with miditok

#155 LiuZH-19 closed 5 months ago
14
Add the possibility to train tokenizer with other token aggregation techniques (WordPiece, Unigram...)

#154 Natooz closed 5 months ago
2
ability to overwrite _create_durations_tuples in init

#153 JLenzy closed 6 months ago
0
allow _create_durations_tuples to be overriden, and new tokenizer loading logic

#152 JLenzy closed 6 months ago
1