Nithin Rao dc9ed88f78 Modify speaker input (#3100) ... * initial_commit Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * init diarizer Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * vad+speaker Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * vad update Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * speaker done Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * initial working version Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * compare outputs Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * added uem support Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * pyannote improvements Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * updated config and script name Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * style fix Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * update Jenkins file Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * jenkins fix Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * jenkins fix Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * update file path in jenkins Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * update file path in jenkins Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * update file path in jenkins Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * jenkins quote fix Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * update offline speaker diarization notebook Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * intial working asr_with_diarization Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * almost done, revist scoring part Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * fixed eval in offline diarization with asr Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * update write2manifest to consider only up to max audio duration Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * asr with diarization notebook Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * Fixed ASR_with_diarization tutorial.ipynb and diarization_utils and edited config yaml file Signed-off-by: Taejin Park <tango4j@gmail.com> * Fixed VAD parameters in Speaker_Diarization_Inference.ipynb Signed-off-by: Taejin Park <tango4j@gmail.com> * Added Jenkins test, doc strings and updated README Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * update jenkins test Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * Doc info in offline_diarization_with_asr Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * Review comments Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> * update outdir paths Signed-off-by: nithinraok <nithinrao.koluguri@gmail.com> Co-authored-by: Taejin Park <tango4j@gmail.com>		2021-11-06 10:55:32 -04:00
..
asr_language_modeling	Change the min value used for masking in Conformer. (#2997)	2021-10-14 00:38:57 -07:00
dataset_processing	Add logging to LS script (#3141)	2021-11-04 16:03:58 -07:00
export	Merge branch 'r1.0.0rc1' into main	2021-03-10 15:40:38 -08:00
freesound_download_resample	Correct ASR issues + Patch for Pytorch 1.8 (#1565)	2020-12-17 14:14:59 -08:00
nemo_legacy_import	Organizing the script folder (#1844)	2021-03-10 15:23:59 -08:00
neural_machine_translation	Fixes bugs in collect_tokenizer_dataset_stats.py (#3060)	2021-10-28 16:04:06 -04:00
nlp_language_modeling	[BigNLP] Merge Megatron GPT to main (#2975)	2021-10-20 21:06:37 -06:00
speaker_tasks	Modify speaker input (#3100)	2021-11-06 10:55:32 -04:00
speech_recognition	Adding bucketing for ASR models with tarred datasets (#2990)	2021-10-13 21:40:50 -07:00
tokenizers	Merge r1.5.0 bugfixes and doc updates to main (#3133)	2021-11-04 10:26:58 -06:00
tts_dataset_files	Remove file (#2855)	2021-09-20 14:17:45 -04:00
voice_activity_detection	VAD postprocessing - binarization, filtering (#2636)	2021-08-12 21:04:03 -07:00
average_model_checkpoints.py	Add optional directory path to reduce checkpoint_path to checkpoint_names (#1637)	2021-01-19 12:54:58 -08:00