From 645f4fc88661918e0c54bf98b63a8b6f8c24b085 Mon Sep 17 00:00:00 2001 From: Eren Golge Date: Tue, 12 Mar 2019 17:02:56 +0100 Subject: [PATCH] config update for nancy --- .compute | 4 ++-- config_cluster.json | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.compute b/.compute index b6bb33dd..71c4d0c1 100644 --- a/.compute +++ b/.compute @@ -3,5 +3,5 @@ ls ${SHARED_DIR}/data/ pip3 install https://download.pytorch.org/whl/cu100/torch-1.0.1.post2-cp36-cp36m-linux_x86_64.whl yes | apt-get install espeak python3 setup.py develop -# python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/keithito/LJSpeech-1.1/ --restore_path ${USER_DIR}/best_model.pth.tar -python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/ +python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/ --restore_path ${USER_DIR}/best_model.pth.tar +# python3 distribute.py --config_path config_cluster.json --data_path ${SHARED_DIR}/data/Blizzard/Nancy/ diff --git a/config_cluster.json b/config_cluster.json index e36bb4c2..e12111be 100644 --- a/config_cluster.json +++ b/config_cluster.json @@ -6,7 +6,7 @@ // Audio processing parameters "num_mels": 80, // size of the mel spec frame. "num_freq": 1025, // number of stft frequency levels. Size of the linear spectogram frame. - "sample_rate": 22050, // wav sample-rate. If different than the original data, it is resampled. + "sample_rate": 16000, // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled. "frame_length_ms": 50, // stft window length in ms. "frame_shift_ms": 12.5, // stft window hop-lengh in ms. "preemphasis": 0.98, // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis. @@ -21,7 +21,7 @@ "clip_norm": true, // clip normalized values into the range. "mel_fmin": 0.0, // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!! "mel_fmax": 8000.0, // maximum freq level for mel-spec. Tune for dataset!! - "do_trim_silence": false // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) + "do_trim_silence": true // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true) }, "distributed":{