| dc.contributor.author | Hernández Mena, Carlos Daniel |
| dc.date.accessioned | 2023-01-03T09:44:08Z |
| dc.date.available | 2023-01-03T09:44:08Z |
| dc.date.issued | 2022-12-08 |
| dc.identifier.uri | http://hdl.handle.net/20.500.12537/305 |
| dc.description | - ENGLISH The "Kaldi Recipe for Faroese" is a code recipe intended to show how to use the corpus "Ravnursson Faroese Speech and Transcripts" [1] to create automatic speech recognition systems using the Kaldi toolkit [2]. - ÍSLENSLA "Kaldi Forskrift fyrir færeysku" er forskrift af því hvernig má nota gagnasafnið "Ravnursson Faroese Speech and Transcripts" [1] til að búa til talgreini í verkfærakistunni Kaldi [2]. [1] Hernández Mena, Carlos Daniel; Simonsen, Annika. "Ravnursson Faroese Speech and Transcripts". Web Downloading: http://hdl.handle.net/20.500.12537/276 [2] Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., ... & Vesely, K. (2011). The Kaldi speech recognition toolkit. In IEEE 2011 workshop on automatic speech recognition and understanding (No. CONF). IEEE Signal Processing Society. |
| dc.language.iso | fao |
| dc.publisher | Reykjavík University |
| dc.rights | Creative Commons - Attribution 4.0 International (CC BY 4.0) |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ |
| dc.rights.label | PUB |
| dc.source.uri | https://github.com/CarlosDanielMena/Kaldi_Recipe_for_Faroese |
| dc.subject | faroese |
| dc.subject | kaldi |
| dc.subject | ASR |
| dc.subject | Speech Recognition |
| dc.subject | Acoustic Model |
| dc.title | Kaldi Recipe for Faroese |
| dc.type | toolService |
| metashare.ResourceInfo#ContentInfo.detailedType | other |
| metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent | true |
| has.files | yes |
| branding | Clarin IS Repository |
| contact.person | Carlos Daniel Hernández Mena carlos.mena@ciempiess.org Reykjavík University |
| files.size | 106244360 |
| files.count | 2 |
Files in this item
Download all files in item (101.32 MB)This item is
Creative Commons - Attribution 4.0 International (CC BY 4.0)
Publicly Available
and licensed under:Creative Commons - Attribution 4.0 International (CC BY 4.0)
- Name
- README.txt
- Size
- 5.38 KB
- Format
- Text file
- Description
- Unknown
- MD5
- d064579c2e4a0b08fe130b947b5f0ce6
-------------------------------------------------------------------------------
Kaldi Recipe for Faroese
-------------------------------------------------------------------------------
Author : Carlos Daniel Hernández Mena.
Programming Languages : Kaldi, Python3, Bash
Recommended use : speech recognition.
-------------------------------------------------------------------------------
Description
-------------------------------------------------------------------------------
The "Kaldi Recipe for Faroese" is a code recipe intended to show how to use
the corpus "Ravnursson Faroese Speech and Transcripts" [1] to create automatic
speech recognition systems using the Kaldi toolkit [2].
In order to set the scripts up, it is necessary to install minimum
requirements and to specify some paths; all of these indicated in the
"run.sh" script of the recipe.
-------------------------------------------------------------------------------
Abou . . .
- Name
- Kaldi_Recipe_for_Faroese.zip
- Size
- 101.32 MB
- Format
- application/zip
- Description
- Unknown
- MD5
- 28ba7ae492920ce1bbe84e631e6e49aa
- Kaldi_Recipe_for_Faroese
- README.txt-1 B
- ravnursson
- s5
- cmd.sh-1 B
- utils18 B
- steps18 B
- conf
- online_cmvn.conf-1 B
- decode.config-1 B
- mfcc_hires.conf-1 B
- mfcc.conf-1 B
- run.sh-1 B
- local
- Prefabricated_Files
- silence_phones.txt-1 B
- extra_questions.txt-1 B
- optional_silence.txt-1 B
- nonsilence_phones.txt-1 B
- etc
- 3GRAM_ARPA_MODEL_PRUNED.lm-1 B
- FAROESE_ASR.dic-1 B
- 4GRAM_ARPA_MODEL.lm-1 B
- create_lexicon.py-1 B
- chain
- run_tdnn_lstm_ADAPTED.sh29 B
- compare_wer_general.sh-1 B
- tuning
- run_lstm_1c.sh-1 B
- run_tdnn_lstm_1r.sh-1 B
- run_tdnn_1f.sh-1 B
- run_tdnn_lstm_1a.sh-1 B
- run_tdnn_lstm_1f.sh-1 B
- run_tdnn_lstm_1k.sh-1 B
- run_lstm_1e_ADAPTED.sh-1 B
- run_lstm_1a.sh-1 B
- run_tdnn_1d.sh-1 B
- run_tdnn_lstm_attention_bs_1a.sh-1 B
- run_tdnn_lstm_1u.sh-1 B
- run_tdnn_lstm_1d.sh-1 B
- run_tdnn_lstm_1i.sh-1 B
- run_tdnn_lstm_1n.sh-1 B
- run_tdnn_1b.sh-1 B
- run_blstm_1a.sh-1 B
- run_lstm_1d.sh-1 B
- run_tdnn_lstm_1s.sh-1 B
- run_tdnn_1g.sh-1 B
- run_tdnn_lstm_1b.sh-1 B
- run_tdnn_lstm_1g.sh-1 B
- run_tdnn_lstm_attention_1a.sh-1 B
- run_tdnn_lstm_1e_disc.sh-1 B
- run_tdnn_lstm_1l.sh-1 B
- run_lstm_1b.sh-1 B
- run_tdnn_1e.sh-1 B
- run_tdnn_lstm_attention_bs_1b.sh-1 B
- run_tdnn_lstm_1v.sh-1 B
- run_tdnn_lstm_1e.sh-1 B
- run_tdnn_lstm_1j.sh-1 B
- run_tdnn_lstm_1o.sh-1 B
- run_tdnn_1c.sh-1 B
- run_lstm_1e.sh-1 B
- run_tdnn_lstm_1t.sh-1 B
- run_tdnn_lstm_1c.sh-1 B
- run_tdnn_lstm_1h.sh-1 B
- run_tdnn_lstm_1m.sh-1 B
- run_tdnn_1a.sh-1 B
- nnet3
- run_tdnn_lstm.sh26 B
- run_tdnn_lstm_disc.sh31 B
- run_tdnn_lstm_lfr.sh30 B
- run_ivector_common_ADAPTED.sh-1 B
- run_tdnn.sh21 B
- run_lstm.sh21 B
- tuning
- run_tdnn_lstm_1c.sh-1 B
- run_lstm_1a.sh-1 B
- run_tdnn_1b.sh-1 B
- run_tdnn_lstm_1b.sh-1 B
- run_tdnn_1a.sh-1 B
- run_tdnn_lstm_1a_disc.sh-1 B
- run_tdnn_lstm_1a.sh-1 B
- run_tdnn_lfr_1a.sh-1 B
- run_tdnn_lstm_1b_disc.sh-1 B
- run_tdnn_1c.sh-1 B
- run_tdnn_lstm_lfr_1a.sh-1 B
- run_blstm.sh-1 B
- compare_wer.sh-1 B
- run_ivector_common.sh-1 B
- score.sh23 B
- corpus_faroese_data_prep.py-1 B
- Prefabricated_Files
- path.sh-1 B
- RESULTS-1 B
- s5