Issues
- 2
SHA hashes in 'main' branch are different from those in the 'origin/main'
#77 opened by KarelVesely84 - 0
Android Espresso not able to test fragement
#75 opened by AbhishekArrk - 1
- 2
- 2
Transformer LM in ASR
#69 opened by marthayifiru - 1
- 37
How can I find Kaldi directory?
#62 opened by Kik099 - 4
SpecAug slows down training time
#56 opened by timolohrenz - 1
- 8
- 1
- 1
- 2
token_text as outputs
#64 opened by valentinp72 - 4
Error in training stage of run_chain_e2e_bichar.sh: 'odict_items' object is not an iterator
#67 opened by mohsen-goodarzi - 1
Google Colab research creation
#63 opened by Kik099 - 1
Stream ASR
#50 opened by Shanboy5566 - 6
Build PyChain with CPU
#54 opened by Shanboy5566 - 4
Getting OOM error at the middle of the training in asr_swbd recipe on lstm encoder decoder model
#60 opened by asifjalal - 1
- 5
- 5
- 1
TypeError: get_asr_dataset_from_json() got an unexpected keyword argument 'combined'
#51 opened by krishnanNuance - 30
Wanna know which recipe involve multi-level LM model train and decoding. Also, can we use word + subword as multi-level decoding ?
#44 opened by PhenixCFLi - 7
- 5
AttributeError: 'SpeechRecognitionEspressoTask' object has no attribute 'feat_dim'
#43 opened by krishnanpooja - 4
Batchnorm and masking
#46 opened by danpovey - 4
GPU utilization is very low
#39 opened by yfliao - 6
Slow training...
#41 opened by maff20 - 1
Support for RNNLM use while decoding?
#42 opened by prashantserai - 6
LM shallow fusion for the Japanese Language.
#38 opened by ken57 - 2
- 1
issues about speech_fconv.py
#35 opened by ZhangChun96 - 2
- 2
Request for recipe for Librispeech 100hr
#33 opened by PhenixCFLi - 17
SWBD Recipe Error
#32 opened by annamine - 2
Deprecated `AT_CHECK` in pychain module
#30 opened by jinpoon - 1
TIMIT Demo example
#28 opened by jedyang97 - 8
- 7
Verify WER by scoring with Kaldi
#17 opened by ahmedalbahnasawy - 1
Using wav2vec with Espresso
#25 opened by MadisKarli - 4
- 2
- 1
please could you explain me how can I train and inference using custom dataset?
#18 opened by lerndeep - 15
- 43
Non-ASCII characters in sample PRD and REF
#11 opened by Shujian2015 - 15
Error in fp16 training
#13 opened by Shujian2015 - 10
tensorized_lookahead_language_model SyntaxError
#10 opened by DTDwind - 5
CUDA OOM issue
#9 opened by Shujian2015 - 2
GPU Distributed Data Parallel Error
#8 opened by roshansh-cmu - 2
SWBD ASR Expected Results- WER
#7 opened by roshansh-cmu