Skip to content

v0.1.0
Compare
Choose a tag to compare
@zhaocq-nlp zhaocq-nlp released this 25 Dec 03:05
· 101 commits to master since this release
v0.1.0
671e88f
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.
  • Basic code structure for Encoder, Decoder, Model, DataPipeline, Tokenizer, Experiment, Metric, and Dataset.
  • (Model) Adds implementation of pre-norm/post-norm Transformer, Speech Transformer, BERT, GPT-2, and Wav2Vec2.0.
  • (Task) Adds implementation of sequence to sequence task and speech to text task (ASR, ST).
  • (DataPipeline, Tokenizer) Adds wrappers for commonly used tokenizers: moses, bpe, jieba, character, sentencepiece, etc.
  • (Dataset) Adds support for reading parallel corpus, speech corpora (libri-trans, MuST-C, and LibriSpeech), and TFRecords.
  • (Experiment) Adds implementation of common training procedure with mixed precision training and various distributed strategies (MirroredStrategy, Horovod, Byteps).
  • (Metric) Adds implementation of BLEU and WER metrics.
  • (Converter) Adds implementation of converting checkpoints from google BERT, OpenAI GPT-2, fairseq Transformer, and fairseq Wav2Vec2.0.
  • Beam search decoding and top-k/p sampling.
  • Supports averaging checkpoints, TFRecord generation, model restoring (see cli/README.md).
  • Step-by-step recipes for training an end-to-end speech translation model (see examples/speech_to_text).
Assets 4
Loading