Alternatives and similar repositories for optimized_transducer

Users that are interested in optimized_transducer are comparing it to the libraries listed below

• k2-fsa / fast_rnnt
  A torch implementation of a recursion which turns out to be useful for RNN-T.
  ☆144Updated 2 years ago
• csukuangfj / transducer-loss-benchmarking
  ☆68Updated 3 years ago
• athena-team / athena-decoder
  ☆76Updated 3 years ago
• TeaPoly / Conformer-Athena
  Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.
  ☆44Updated 2 years ago
• 1ytic / warp-rna
  Recurrent Neural Aligner
  ☆50Updated 5 years ago
• TeaPoly / CTC-OptimizedLoss
  Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.
  ☆58Updated 2 years ago
• iamjanvijay / rnnt_decoder_cuda
  An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.
  ☆68Updated 4 years ago
• HaoranMiao / streaming-attention
  streaming attention networks for end-to-end automatic speech recognition
  ☆55Updated 5 years ago
• MarkWuNLP / SemanticMask
  The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"
  ☆38Updated 5 years ago
• tencent-ailab / 3m-asr
  3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition
  ☆118Updated 3 years ago
• csukuangfj / kaldilm
  Python wrapper for kaldi's arpa2fst
  ☆38Updated 2 weeks ago
• idiap / pkwrap
  A pytorch wrapper for LF-MMI training and parallel training in Kaldi
  ☆73Updated 3 years ago
• chenjiasheng / mwer
  mWER loss implementation in tensorflow
  ☆31Updated 5 years ago
• cornerfarmer / ctc_segmentation
  Segment a given audio into utterances using a trained end-to-end ASR model.
  ☆73Updated 4 years ago
• asappresearch / multistream-cnn
  Multistream CNN for Robust Acoustic Modeling
  ☆40Updated 4 years ago
• YiwenShaoStephen / pychain_example
  ☆48Updated 4 years ago
• hainan-xv / PASM
  Pronunciation-assisted Subword Modeling
  ☆31Updated 6 years ago
• TeaPoly / CE-OptimizedLoss
  Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…
  ☆22Updated 11 months ago
• csukuangfj / kaldi_native_io
  python wrapper for kaldi's native I/O
  ☆27Updated 8 months ago
• wenet-e2e / WeTextProcessing.deprecated
  ☆61Updated 2 years ago
• k2-fsa / multi_quantization
  ☆44Updated last year
• oshindow / Transformer-Transducer
  A pytorch_lightning reimplementation of the Transducer module from ESPnet.
  ☆77Updated 4 years ago
• George0828Zhang / torch_cif
  A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/ab…
  ☆33Updated last year
• athena-team / DiDiSpeech
  ☆44Updated 4 years ago
• upskyy / Transformer-Transducer
  PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASS…
  ☆108Updated 3 years ago
• Slyne / ctc_decoder
  A ctc decoder for both online and offline asr model
  ☆64Updated last year
• jctian98 / e2e_lfmmi
  E2E system with LF-MMI; word N-gram for Mandarin
  ☆166Updated 3 years ago
• thuhcsi / FlatTN
  Chinese Text Normalization and Dataset
  ☆85Updated 3 years ago
• k2-fsa / kaldifst
  Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files
  ☆53Updated last week
• pzelasko / kaldialign
  Python wrappers for Kaldi Levenshtein's distance and alignment code.
  ☆68Updated 3 months ago