#!/bin/bash

set -xe

apt-get install -y python3-venv
python3 -m venv /tmp/venv
source /tmp/venv/bin/activate

pip install -r <(grep -v tensorflow requirements.txt)
pip install tensorflow-gpu==1.14.0

# Install ds_ctcdecoder package from TaskCluster
pip install $(python3 util/taskcluster.py --decoder)

mkdir -p ../keep/summaries

data="${SHARED_DIR}/data"
fis="${data}/LDC/fisher"
swb="${data}/LDC/LDC97S62/swb"
lbs="${data}/OpenSLR/LibriSpeech/librivox"

python -u DeepSpeech.py \
  --train_files "${fis}-train.csv","${swb}-train.csv","${lbs}-train-clean-100.csv","${lbs}-train-clean-360.csv","${lbs}-train-other-500.csv" \
  --dev_files "${lbs}-dev-clean.csv"\
  --test_files "${lbs}-test-clean.csv" \
  --train_batch_size 24 \
  --dev_batch_size 48 \
  --test_batch_size 48 \
  --n_hidden 2048 \
  --learning_rate 0.0001 \
  --dropout_rate 0.2 \
  --epoch 13 \
  --checkpoint_dir "../keep" \
  --summary_dir "../keep/summaries"