gooofy/zamia-speech

Issues

• Download page not available

  #121 opened a year ago by AnjaRy
  0

• Binaries are no longer available

  #120 opened 2 years ago by pguyot
  1

• Model Adaption

  #93 opened a year ago by jbaudisch
  1

• Accuracy numbers

  #82 opened 2 years ago by MattWiethoff
  1

• Est_republicaine Corpus not found

  #110 opened 4 years ago by BaderEddineB
  6

• Install on a Raspberry Pi 4

  #102 opened 5 years ago by sushipan
  9

• Raspberry Pi 4 Raspbian Buster Installation

  #76 opened 5 years ago by OTTStreamingVideo
  6

• Using Language Models to decode.

  #119 opened 3 years ago by IanMGriff
  0

• Change language - Zamia

  #118 opened 3 years ago by Ascendina
  2

• Install Zamia-speech English nnet3-chain model on Ubuntu

  #117 opened 3 years ago by pengcheng-tech
  0

• Adding new word in the vocabulary

  #79 opened 5 years ago by ckobus
  25

• Kaldi nnet3 without ivector model

  #116 opened 4 years ago by abramovi
  1

• add processing files for mozilla cv corpus v2

  #73 opened 5 years ago by cogmeta
  3

• Suggestion for extracting CNRTL Est Républicain Corpus

  #99 opened 5 years ago by tattorba87
  1

• Speech corpus sentences extraction !

  #113 opened 4 years ago by BaderEddineB
  0

• Batch Inference

  #109 opened 4 years ago by rockiram
  2

• https://goofy.zamia.org/repo-ai/raspbian/stretch/armhf/bofh.asc - permission denied?

  #108 opened 4 years ago by Arkert
  0

• retrain existing nnet3 model with more data

  #106 opened 5 years ago by cogmeta
  3

• GMM decoding

  #107 opened 5 years ago by sitobock
  0

• Question: Decoding with Zamia Speech's German wav2letter model using wav2letter Decoder executable

  #104 opened 5 years ago by realbaker1967
  8

• Training wav2letter++ streaming convnets (TDS + CTC)

  #101 opened 5 years ago by erksch
  6

• Errors while trying to add new words

  #105 opened 5 years ago by ammyt
  3

• How to use the wav2letter model

  #80 opened 5 years ago by brunce
  1

• Cite in a paper?

  #103 opened 5 years ago by synesthesiam
  1

• Error 403 at goofy.zamia.org/repo-ai/

  #97 opened 5 years ago by jumper047
  5

• German Distant Speech Dataset

  #100 opened 5 years ago by BeWe11
  2

• Training for tdnn_sp

  #92 opened 5 years ago by dpny518
  4

• tdnn_f vs tdnn_fl

  #98 opened 5 years ago by dpny518
  0

• Apt Error: The following signatures were invalid

  #89 opened 5 years ago by chrisspen
  4

• Number of epoch needed on 3000 hours data

  #96 opened 5 years ago by cogmeta
  6

• where to find the lattices?

  #95 opened 5 years ago by besimali
  3

• When trying to following instruction ,I am getting "signatures were invalid "error

  #85 opened 5 years ago by WilliamVJacob
  9

• exporting final model ready for serving after successful training

  #94 opened 5 years ago by cogmeta
  2

• No such file exp/nnet3_chain/extractor/final.ie

  #90 opened 5 years ago by cogmeta
  2

• python3-kaldiasr : Depends: python3 (< 3.6) but 3.6.7-1~18.04 is to be installed

  #91 opened 5 years ago by edbir1
  2

• install french model

  #88 opened 5 years ago by lespiaucq
  1

• Binary AI Packages for arm64 architecture

  #67 opened 5 years ago by nsxr51
  2

• Which language models were used to generate G.fst for the pre-trained Kaldi models

  #87 opened 5 years ago by lightalchemist
  0

• Integrating it in ios

  #84 opened 5 years ago by Amanpradhan
  0

• Problems installing

  #83 opened 5 years ago by maltejanssen
  4

• run time error

  #64 opened 5 years ago by SibtainRazaJamali
  1

• Cant install as per the instructions

  #81 opened 5 years ago by jamesamrundle
  2

• Hardware requirements to trains Kaldi models

  #72 opened 5 years ago by OleksandrChekmez
  4

• Permisson denied when trying to install zamia speech on Ubuntu?

  #74 opened 5 years ago by lukaguinan
  1

• how to create decode data from socket recording audio ?

  #71 opened 5 years ago by forkballpitch
  1

• DNN miss alignment

  #70 opened 5 years ago by dpny518
  2

• phone '

  #69 opened 5 years ago by dpny518
  2

• nspc

  #66 opened 5 years ago by dpny518
  2

• w2l_env_activate,w2l_train default values in speechrc

  #68 opened 5 years ago by cogmeta
  6

• ipa and oovs

  #65 opened 5 years ago by xfwu
  4