summaryrefslogtreecommitdiff
path: root/tools/download-parakeet.sh
diff options
context:
space:
mode:
Diffstat (limited to 'tools/download-parakeet.sh')
-rwxr-xr-xtools/download-parakeet.sh33
1 files changed, 33 insertions, 0 deletions
diff --git a/tools/download-parakeet.sh b/tools/download-parakeet.sh
new file mode 100755
index 0000000..cb6fafc
--- /dev/null
+++ b/tools/download-parakeet.sh
@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+# Downloads NVIDIA Parakeet TDT 0.6B v3 (int8) plus the Silero VAD model into a
+# folder whose layout matches what RECCoon expects on the device.
+#
+# Usage:
+# ./download-parakeet.sh [output-dir] (default: ./reccoon-models)
+#
+# Then copy the output directory to the device, e.g.:
+# adb push reccoon-models/ /sdcard/Android/data/com.wuhei.reccoon/files/models/
+set -euo pipefail
+
+OUT="${1:-reccoon-models}"
+PARAKEET="https://huggingface.co/csukuangfj/sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8/resolve/main"
+VAD="https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/silero_vad.onnx"
+
+mkdir -p "$OUT/parakeet-v3"
+
+echo "==> Silero VAD"
+curl -L --fail -o "$OUT/silero_vad.onnx" "$VAD"
+
+echo "==> Parakeet v3 (encoder is ~652 MB, this can take a while)"
+for file in encoder.int8.onnx decoder.int8.onnx joiner.int8.onnx tokens.txt; do
+ echo " -> $file"
+ curl -L --fail -o "$OUT/parakeet-v3/$file" "$PARAKEET/$file"
+done
+
+echo
+echo "Done. Layout:"
+find "$OUT" -type f -printf ' %p (%s bytes)\n'
+echo
+echo "On the phone these must live under:"
+echo " /sdcard/Android/data/com.wuhei.reccoon/files/models/"
+echo "i.e. .../models/silero_vad.onnx and .../models/parakeet-v3/*.onnx"