Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • 278-padding-tokens-are-not-ignored-during-training
  • 281-add-support-for-prompting
  • 308-support-rotation-on-dan-dataset-extraction
  • 35-new-function-to-aggregate-attention-maps
  • 35-new-function-to-aggregate-attention-maps-2
  • attention-recital
  • bump-albumentations
  • bump-black
  • bump-boto3
  • bump-fontTools
  • bump-griffe
  • bump-imageio
  • bump-lxml
  • bump-matplotlib
  • bump-mkdocs
  • bump-mkdocs-material
  • bump-mkdocstrings
  • bump-mkdocstrings-python
  • bump-mlflow
  • bump-mlflow-skinny
  • attention-exp
  • 0.2.2b2
  • 0.2.2b1
  • 0.2.2a2
  • 0.2.2a1
  • 0.2.1
  • 0.2.0
  • 0.2.0rc12
  • 0.2.0rc11
  • 0.2.0rc10
  • 0.2.0rc9
  • 0.2.0rc8
  • 0.2.0rc7
  • 0.2.0rc6
  • 0.2.0rc5
  • 0.2.0rc4
  • 0.2.0rc3
  • 0.2.0rc2
  • 0.2.0rc1
  • 0.2.0-dev6
40 results
Created with Raphaël 2.2.018Oct1716131110429Sep282722151413115131Aug30292822211817161412109874331Jul2524201918171311107654330Jun29282726232220161514131298730May2926252423221716151211104228Apr14131254324Mar2322211514873227Feb2422161510131Jan26255414Dec98625Nov2322171528Oct2619May26Apr1228Mar241811104fix augno preprocesscast to float32deletionFlat in-memintegers + ctypesMultiprocessing arrayUse disk to save preprocessMissing returnMissing caseInvalid assertSample classDebugFix typosWIPRetry image downloadDeprecation warning as flashlight-text will not be bundled in later versions of torchaudioSave dropout scheduler step_numNew mode to split prediction by starting tokensAdd Language Model DecoderRound mean values calculated during data analysisDocumentation: Remove submodule mentionsAllow element with no transcriptionLog when removing bested checkpointCharset should only include training charactersAdd default values for entity separatorsRemove the `load_entities` parameter from the `extract` commandRed backgroundFix resizingUse multithreading to download images at the end, remove cache as we now...Fix lintmulti-dan-perce…multi-dan-perceiverSave best modelMerge Perceiver codeUse configuration file and update evaluation codeDo not use language charsetsMove ml_train to ocr folderSupport multiple training datasetsError in _valid_image_formatNormalize prediction output formatUse line image extractor from PyPi instead of submodule