Alternatives and similar repositories for kaldi_native_io:

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

• csukuangfj / kaldilm
  Python wrapper for kaldi's arpa2fst
  ☆38Updated 2 months ago
• k2-fsa / kaldifst
  Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files
  ☆47Updated 7 months ago
• csukuangfj / kaldi-hmm-gmm
  ☆25Updated 3 months ago
• idiap / icassp-oov-recognition
  Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"
  ☆17Updated 3 years ago
• fgnt / mms_msg
  Multipurpose Multi Speaker Mixture Signal Generator
  ☆44Updated 2 weeks ago
• juxiangyu / kaldi_hclg_chinese_tutorial
  use 3 chinese senteces as training corpus to show how to build lm model and HCLG decoding graph
  ☆8Updated 4 years ago
• hainan-xv / PASM
  Pronunciation-assisted Subword Modeling
  ☆29Updated 5 years ago
• qiujiali / lattice-rescore
  ☆16Updated 2 years ago
• pzelasko / kaldialign
  Python wrappers for Kaldi Levenshtein's distance and alignment code.
  ☆62Updated 11 months ago
• Diamondfan / cassnat_asr
  Implementation of CTC alignment-based single step non-autoregressive transformer
  ☆13Updated last year
• BUTSpeechFIT / ASR-hybrid-decoding
  ☆16Updated 5 years ago
• csukuangfj / optimized_transducer
  Memory efficient transducer loss computation
  ☆68Updated 2 years ago
• luomingshuang / k2-speechbrain
  In this repository, I try to combine k2 with speechbrain to decode well and fastly.
  ☆16Updated 2 years ago
• HaoranMiao / streaming-attention
  streaming attention networks for end-to-end automatic speech recognition
  ☆55Updated 4 years ago
• lawlict / EEND_loss
  End-to-end diarization loss
  ☆22Updated 3 years ago
• wangkenpu / WSJ2WAV
  Convert WSJ sphere format to waveform and do data simulation.
  ☆16Updated 5 years ago
• k2-fsa / kaldi-decoder
  Decoders from Kaldi using OpenFst
  ☆26Updated last month
• MarkWuNLP / SemanticMask
  The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"
  ☆38Updated 4 years ago
• HuangZiliAndy / SSL_for_multitalker
  ADAPTING SELF-SUPERVISED MODELS TO MULTI-TALKER SPEECH RECOGNITION USING SPEAKER EMBEDDINGS
  ☆28Updated last year
• yuhangear / wenet-android
  ☆11Updated 3 years ago
• aispeech-lab / WASE
  PyTorch implementation of WASE described in our ICASSP 2021: "Wase: Learning When to Attend for Speaker Extraction in Cocktail Party Envi…
  ☆24Updated 3 years ago
• athena-team / athena-decoder
  ☆75Updated 2 years ago
• csukuangfj / transducer-loss-benchmarking
  ☆68Updated 2 years ago
• wenet-e2e / wesignal
  Production first, nn-based on-device signal processing toolkit.
  ☆64Updated last year
• 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…
  ☆20Updated 4 months ago
• k2-fsa / multi_quantization
  ☆43Updated last year
• nttcslab-sp / torchain
  WIP: pytorch FFI wrapper for Kaldi chain loss (a.k.a. Lattice Free MMI)
  ☆20Updated 6 years ago
• pkufool / simple-wer
  A simple command line tool to calculate WER for ASR.
  ☆14Updated 4 months ago
• jtrmal / kaldi2020
  ☆27Updated 4 years ago
• shinjiwlab / cmu_multilingual_speech
  CMU multilingual speech repository
  ☆31Updated 2 years ago