srvk/eesen

Issues

• Can not run training program with cuda 10.2

  #220 opened 5 years ago by t13m
  3

• Librispeech - Training starting error

  #221 opened 5 years ago by omprakashsonie
  3

• Determinizability of TLG.fst in the phonetic case

  #222 opened 4 years ago by oleksii-a
  0

• Why do we need to compile the tokens to FST in wsj recipe?

  #219 opened 5 years ago by Joefi
  0

• Why do we need space and unk symbols in the char mode for acoustic model?

  #218 opened 5 years ago by wizardk
  6

• KALDI_ASSERT: at train-ctc-parallel:AddMatMat:cuda-matrix.cc:570, failed: m == NumCols()

  #217 opened 5 years ago by icestoneking
  0

• Read failure in ReadBasicType, file position is -1, next char is -1

  #216 opened 5 years ago by icestoneking
  0

• Error when training Librispeech recipe

  #161 opened 7 years ago by z430
  2

• Missing label.counts

  #203 opened 6 years ago by tony-stark1
  3

• Cannot install openfst-1.4.1

  #215 opened 5 years ago by JeromeNi
  2

• Installing error

  #211 opened 6 years ago by hdubey
  8

• LatticeFasterDecoder failed with "link_extra_cost == link_extra_cost"

  #214 opened 5 years ago by feihwu
  1

• Training Error when run tedlium recipe

  #213 opened 6 years ago by yuexianghubit
  2

• Error Decoding : Tedlium example

  #172 opened 7 years ago by aheba
  7

• Clarification Regarding Using WFST decoding

  #210 opened 6 years ago by rmalav15
  1

• Difference between decode-faster vs. latgen-faster

  #159 opened 7 years ago by stefbraun
  4

• Potential overflow when calculating exp

  #209 opened 6 years ago by HaisongDing
  0

• when the final decoding error

  #185 opened 6 years ago by 13265170340
  3

• failed: Dim() == v.Dim()

  #208 opened 6 years ago by rezame
  2

• install errors

  #176 opened 6 years ago by ben-8878
  7

• Error when composing decoding graph using ls_decode_graph.sh

  #192 opened 6 years ago by sundeepteki
  2

• Query on LibriSpeech Character Error Rate

  #204 opened 6 years ago by Pradeep-Rangan
  2

• Memory Leak

  #207 opened 6 years ago by moodeerf
  1

• Problem with EESEN installation

  #179 opened 7 years ago by iglov
  11

• difference in output labels

  #205 opened 6 years ago by HariKrishna-Vydana
  1

• Learning rate scheduling

  #195 opened 6 years ago by efosler
  12

• DeepBiLSTM

  #201 opened 6 years ago by efosler
  2

• Clean up v2 for swb

  #200 opened 6 years ago by ramonsanabria
  0

• Synchronous SGD

  #197 opened 6 years ago by ramonsanabria
  1

• [tf_clean] swb1/v1-tf WFST decoding - checking on assumptions

  #193 opened 6 years ago by efosler
  43

• [tf_clean] CTC logits/posteriors/etc for augmented input buggy in tf_test.py

  #194 opened 6 years ago by efosler
  6

• [tf_clean] check add in installation and push adaptation to tf 1.8

  #191 opened 6 years ago by ramonsanabria
  0

• [tf-clean] adapt char creation from the master branch code

  #190 opened 6 years ago by ramonsanabria
  0

• tf_clean swbd v1-tf: illegal argument batch_size passed from run_ctc_phn.sh

  #189 opened 6 years ago by efosler
  2

• OpenFST install hangs (forever?)

  #180 opened 6 years ago by riebling
  3

• Issue during installation - not in gzip format

  #184 opened 7 years ago by Rashmi39
  0

• Problems during the training phase of the model

  #182 opened 7 years ago by 13265170340
  2

• data perepration

  #177 opened 7 years ago by akbar20gh
  5

• steps/train_ctc_parallel.sh failed

  #178 opened 7 years ago by niucheney
  0

• can eesen do gop ？

  #174 opened 7 years ago by Duum
  0

• Query - How is RNN-LM used while deocding

  #175 opened 7 years ago by mineshmathew
  1

• Missing labels in training / decoding in tf_clean branch

  #169 opened 7 years ago by martiansideofthemoon
  13

• INSTALLATION Problem : Libtool on Ubuntu

  #171 opened 7 years ago by aheba
  0

• decoding without the language model

  #167 opened 7 years ago by HariKrishna-Vydana
  2

• is latest eesen version very different from eesen-master

  #166 opened 7 years ago by HariKrishna-Vydana
  2

• does eesen support Asynchronous Stochastic Gradient Descent? Thanks!

  #165 opened 7 years ago by feina1
  2

• method for adding embedings to hidden layers while training

  #164 opened 7 years ago by HariKrishna-Vydana
  1

• Importance of utterance lengths

  #156 opened 7 years ago by ericbolo
  5

• decoding log-posteriors with eesen

  #158 opened 7 years ago by sanakhamekhem
  5

• transcript to phone sequence

  #157 opened 7 years ago by jinserk
  11