MozillaItalia/DeepSpeech-Italian-Model
Tooling for producing Italian model (public release available) for DeepSpeech and text corpus
PythonGPL-3.0
Issues
- 2
Docker build fail
#135 opened by FrancescoMontedori - 0
Migrate to Coqui
#134 opened by Mte90 - 5
- 11
Generate an Italian text corpus
#36 opened by Mte90 - 4
Other italian models for transfer learning
#116 opened by DanBmh - 4
- 10
LIST OF AUDIO+TEXT DATASETS
#114 opened by nefastosaturo - 2
- 3
Project license
#131 opened by Mte90 - 9
MLS and MAILABS: considerations and issues ( Have you seen my apostrophe?)
#124 opened by nefastosaturo - 3
Experiment on creating a new dataset audio+text
#107 opened by Mte90 - 4
- 3
Voxforge bad samples, help for cleaning up
#111 opened by nefastosaturo - 3
MITADS - new corpora to import
#117 opened by eziolotta - 1
Really bad results on Raspberry Pi 4
#115 opened by lunard - 2
- 4
MITADS - Transcript roman numbers
#100 opened by Mte90 - 6
Improve download status for Mitads
#84 opened by Mte90 - 8
Archive audio+text to download
#90 opened by Mte90 - 3
Define general rules for all sentences
#78 opened by mone27 - 0
- 1
- 0
Readme improvements
#101 opened by Mte90 - 1
Evaluate Voci Parlate of Wikipedia
#34 opened by Mte90 - 4
deepspeech - lm.binary and trie: how to?
#104 opened by pico977 - 7
Change Mitads to another name on public release
#65 opened by Mte90 - 2
Training pipeline
#92 opened by nefastosaturo - 1
Create the "contributing" file
#106 opened by Sav22999 - 9
Not clear how to do a simple speech recognition
#102 opened by foosoftsrlold - 4
Document docker env variables
#93 opened by Mte90 - 8
deepspeech.Model() fails: AttributeError: 'Model' object has no attribute '_impl'
#66 opened by ccolonna - 1
Trascrizioni Borgo Manero
#89 opened by Mte90 - 0
- 6
Wrapper script for corpus generation
#41 opened by Mte90 - 3
[output cleaning] ted_importer.py
#61 opened by nefastosaturo - 2
Supporto per sviluppo
#67 opened by cooked - 1
Trie file Generation
#68 opened by smark- - 2
Create a tiny sample from the CV dataset
#48 opened by Mte90 - 0
[output cleaning] qallme_importer.py
#62 opened by nefastosaturo - 0
[output cleaning] eulogos importer
#63 opened by nefastosaturo - 0
Parallelize OpenSubtitles exporter
#57 opened by marco-c - 3
- 0
Add docs to generate the model in readme
#46 opened by Mte90 - 0
Align repo
#43 opened by Mte90 - 0
Update the CV dataset
#44 opened by Mte90 - 3
Document Corpus scripts
#42 opened by Mte90 - 1
Evaluate MPSKA dataset
#37 opened by Mte90 - 0
Align with the original repo
#32 opened by Mte90 - 1
- 0
Align with french repository
#27 opened by Mte90