Aleksey Grinchuk (Oleksii Hrinchuk)

[WIP] TTS tokenizers moved to collections.common.tokenizers

3

# What does this PR do ? Move TTS tokenizers to collections.common.tokenizers so they can be used in cross-collections pipelines. For implementing ASR/ST model training which generates samples on-the-fly with...

Architecture for word-level Penn Treebank dataset

5

Hello! Can you, please, provide the bash script for training Transformer-XL on PTB dataset with PyTorch? Thanks!

Penn Treebank and WikiText-2 architectures

1

Hello! Could you, please, provide hyperparameters for training models with close to SOTA perplexity on PTB and WT2 (if you experimented with the latter, as it has the corresponding choice...

Yttm deprecation

1

# What does this PR do ? Deprecate YouTokenToMe library which was abandoned. **Collection**: common, nlp # Changelog - Add specific line by line info of high level changes in...