Platalea v2.1

What's Changed

• Mainly, this release adds preprocessing and a dataloader for the howto100m dataset of howto videos. This has not yet been tested thoroughly.
• Bugfix in rank_eval.py

Full Changelog: v2.0...v2.1

Platalea v2.0

Changes related to the ZeroSpeech challenge:

• added support for SpokenCOCO dataset
• added code to support the use of pretrained features + utility script to extract CPC features
• refactored tokenization helpers making the tokenizer a global variable of dataset.py
• changed platalea default config path ~/.platalea -> ~/.config/platalea
• disabled use of wandb by default in basic.py and transformer.py experiments
• pinning down pytorch version

Resolves issues #53, #103, #104 and (temporarily) solves #116.

Platalea v1.0

Introducing an attention-based encoder-decoder architecture for speech recognition. Multitask training with multiple objectives (e.g. cross-modality retrieval and speech transcription) is also possible now.

v0.9

Update datafiles.md