From 987e22bffb94115bd1c5f58f14251dcc8fb38f80 Mon Sep 17 00:00:00 2001 From: Michael Hansen Date: Fri, 9 Oct 2020 15:12:23 -0400 Subject: [PATCH] Add README --- README.md | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) create mode 100644 README.md diff --git a/README.md b/README.md new file mode 100644 index 0000000..089197f --- /dev/null +++ b/README.md @@ -0,0 +1,20 @@ +# Czech Kaldi Profile + +A [Rhasspy](https://github.com/rhasspy/rhasspy) profile for Czech (`cs`). + +Includes: + +* A [Kaldi nnet3](https://kaldi-asr.org/doc/dnn3.html) speech to text model + * See files in `acoustic_model/` + * Recipe created with [ipa2kaldi](https://github.com/rhasspy/ipa2kaldi) + * Trained on: + * [Vystadial VOIP](http://www.openslr.org/6/) (18.2 hours) + * [Common Voice](https://commonvoice.mozilla.org) (26.6 hours) +* An [IPA](https://en.wikipedia.org/wiki/International_Phonetic_Alphabet) pronunciation lexicon pulled from [Wiktionary](https://www.wiktionary.org/) + * See `base_dictionary.txt.gz` +* A [phonetisaurus](https://github.com/AdolfVonKleist/Phonetisaurus) grapheme to phoneme model for predicting word pronunciations + * See `g2p.fst.gz` + * Trained on `base_dictionary.txt.gz` +* A tri-gram [ARPA language model](https://cmusphinx.github.io/wiki/arpaformat/) + * See `base_language_model.txt.gz` + * Text from audio transcriptions and [Universal Dependencies](https://universaldependencies.org/)