Skip to content
Snippets Groups Projects
Select Git revision
  • master default protected
1 result
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.027Sep9Jul8732129Jun28272625242322201917151413111076543129May28272322201716151413111098752130Apr29272625242322201918171615141197643131Mar3029272423212019181716141312111087654127Feb262120181486432130Jan262221171615141312119876542131Dec30282624232117151312117543130Nov292827262522211917161514131298765131Oct3027201817151312109875432128Sep262520191817161514131211765432131Aug3029282725242322212019181716151413121198764231Jul28272625242221181716151210976532129Jun27252019181514131110986532131May302926252423222119181715141097653130Apr29272625[egs] Fix reference to decode_wav_with_nnet3.sh in READMEmastermaster[egs] Add my-commonvoice directory for commonvoice training[scripts] Fix to steps/nnet/train.sh (nnet1) w.r.t. incorrect bash test expressions (#3456)[scripts] Make segment_long_utterance honor frame_shift (#3455)[src,scripts,egs] Add code and example for SpecAugment in nnet3 (#3449)[scripts] Extend utils/data/subsegment_data_dir.sh to copy reco2dur (#3452)[scripts] Scripts for VB (variational bayes) resegmentation for Callhome diarization (#3305)[src,scripts] Various typo fixes and stylistic fixes (#3153)[src] Fix to a check in nnet-compute code (#3447)[scripts] Fix shebang of taint_ctm_edits.py to invoke python3 directly (#3445)[src] Cuda decoder fixes, efficiency improvements (#3443)[egs] Fix perl encoding bug (was causing crashes) (#3442)[src] Marking operator as __host__ __device__ to avoid build issues (#3441)[build] Fix the cross-compiling issue for Android under MacOS (#3435)[src] Update Insert function of hashlist and decoders (#3402) (#3438)Revert "[src] Update Insert function of hashlist and decoders (#3402)" (#3436)[egs] Fix encoding issues in Chinese ASR recipe (#3430) (#3434)[build] Add missing deps to cuda makefiles, thanks: yiyidhuang@gmail.com (#3432)[build] Fix to cuda makefiles, thanks: yiyidhuang@gmail.com (#3431)[egs] Small fix to aspire run_tdnn_7b.sh (#3429)[build] Add missing lib dependency in cudafeatbin (#3427)[src] Adding missing thread.join in CUDA decoder and fixing two todos (#3428)[src] Remove outdated comment (#3148) (#3422)[egs] Replace $cuda_cmd with $train_cmd for FarsDat (#3426)[src] Enable an option to use the GPU for feature extraction in GPU decoding (#3420)[build] Fix configure bug RE CuSolver (#3417)[src] Fix spelling mistake in #3415 (#3416)[src] Update Insert function of hashlist and decoders (#3402)[src] Fix build of online feature extraction with older CUDA version (#3415)[src] Fix CUDA_VSERION number in preprocessor checks (#3414)[src] Added error string to CUDA allocation errors. (#3413)[src] Fix build error introducted by race condition in PR requests/accepts. (#3412)[src] Added GPU feature extraction (will improve speed of GPU decoding) (#3390)[scripts] Fix to checks in adjust_unk_graph.sh (#3410)[src] Remove debugging assert in cuda feature extraction code (#3411)[src] online2-tcp, add option to display start/end times (#3399)[egs] Fix to separators in Aspire, related to #3408 (#3409)[egs] Fix to separators in Aspire reverb recipe (#3408)[src] Make stack trace display more user friendly (#3406)[src] Change functions like AppiyLog() to all work out-of-place (#3185)