From 04347e67c6f87ee7a33c8ed8103aecebac6c3888 Mon Sep 17 00:00:00 2001 From: Jean-Marc Valin Date: Wed, 10 Apr 2024 02:02:59 -0400 Subject: [PATCH] Missing blockquotes --- dnn/torch/fargan/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/dnn/torch/fargan/README.md b/dnn/torch/fargan/README.md index 21124c716..a92c914dc 100644 --- a/dnn/torch/fargan/README.md +++ b/dnn/torch/fargan/README.md @@ -8,9 +8,9 @@ For data preparation you need to build Opus as detailed in the top-level README. You will need to use the --enable-deep-plc configure option. The build will produce an executable named "dump_data". To prepare the training data, run: - +``` ./dump_data -train in_speech.pcm out_features.f32 out_speech.pcm - +``` Where the in_speech.pcm speech file is a raw 16-bit PCM file sampled at 16 kHz. The speech data used for training the model can be found at: https://media.xiph.org/lpcnet/speech/tts_speech_negative_16k.sw