-
DeepSeekV3MoE Public
DeepSeek V3 MoE with aux-loss-free and sequence aux loss.
-
CE-OptimizedLoss Public
Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Pooling Loss.
-
matmulfreellm Public
Forked from ridgerchu/matmulfreellmImplementation for MatMul-free LM.
-
wenet Public
Forked from wenet-e2e/wenetProduction First and Production Ready End-to-End Speech Recognition Toolkit
Python Apache License 2.0 UpdatedJun 3, 2024 -
you-get Public
Forked from soimort/you-get⏬ Dumb downloader that scrapes the web
Python Other UpdatedMay 10, 2024 -
NSD-MS2S Public
Forked from liyunlongaaa/NSD-MS2SCHIME-7 diarization champion system: neural speaker diarization using memory-aware multi-speaker embedding with sequence-to-sequence architecture
Shell UpdatedFeb 8, 2024 -
AIF-PyTorch Public
(NOT Official) Implementation Auto-regressive Integrate-and-Fire (AIF)
-
CTC-OptimizedLoss Public
Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.
-
PLCPA-ASYM-Loss Public
The power-law compressed phase-aware asymmetric (PLCPA-ASYM) loss
-
self_attention_alignment Public
Forked from lhwcv/self_attention_alignmentDeep model with built-in self-attention alignment for acoustic echo cancellation, Pytorch implement
Python MIT License UpdatedMay 30, 2023 -
nara_wpe Public
Forked from fgnt/nara_wpeDifferent implementations of "Weighted Prediction Error" for speech dereverberation
Python MIT License UpdatedMar 16, 2023 -
-
FunASR Public
Forked from modelscope/FunASRA Fundamental End-to-End Speech Recognition Toolkit
Python MIT License UpdatedDec 2, 2022 -
-
speexdsp-ns-python Public
Python bindings of speexdsp noise suppression library
-
Conformer-Athena Public
Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.
-
NKF-AEC Public
Forked from fjiang9/NKF-AECAcoustic Echo Cancellation with Nerual Kalman Filtering
HTML UpdatedSep 13, 2022 -
torchdistance Public
Forked from francescocastelli/torchdistanceEdit-distance PyTorch extension with Cpu and CUDA kernels
Python UpdatedApr 6, 2022 -
asr_frontend Public
PyTorch implementation of frontend, like PCEN (per-channel energy normalization) and Mel-Filterbank (mel-filterbank).
-
PercepNet Public
Forked from jzi040941/PercepNet(Work In Progress) Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech
-
SpectrumAugmenter Public
Performs data augmentation as according to the SpecAugment paper. Modified from Lingvo (TensorFlow > 1.10.0).
-
rir-configuration-generator Public
Generation of virtual rooms configurations.
-
warp-ctc-crf Public
An extension of thu-spmi/CAT which contains a full-fledged implementation of CTC-CRF for Tensorflow.
-
-
unified2021 Public
Forked from nay0648/unified2021A UNIFIED SPEECH ENHANCEMENT FRONT-END FOR ONLINE DEREVERBERATION, ACOUSTIC ECHO CANCELLATION, AND SOURCE SEPARATION
-
speechbrain Public
Forked from speechbrain/speechbrainA PyTorch-based Speech Toolkit
Python Apache License 2.0 UpdatedMar 17, 2021 -
warp-rnnt Public
Forked from 1ytic/warp-rnntCUDA-Warp RNN-Transducer with TensorFlow and PyTorch binding.
-
athena Public
Forked from athena-team/athenaan open-source implementation of sequence-to-sequence based speech processing engine
Python Apache License 2.0 UpdatedNov 12, 2020 -
-
cat_tensorflow Public
Crf-based Asr Toolkit with TensorFlow implement
{{ message }}