Skip to content

Fix outdated AudioSet link, shared memory, and TypeError #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ayaadev wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Fix outdated AudioSet link, shared memory, and TypeError #5

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
95b35a3
Fix outdated AudioSet link
ayaadev Mar 27, 2026
3fb4f75
Set IPC to host in Docker compose
ayaadev Mar 28, 2026
9986f5e
Pin protobuf package to 3.20.x
ayaadev Mar 28, 2026
7eb8627
Inform the user that the finished model could be small
ayaadev Mar 28, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,8 @@ docker compose run --rm trainer python train.py --wake-word "hey cal" --data-dir

Training takes 4-8 hours depending on GPU.

Don't be alarmed if the finished model is only a few hundred kilobytes. Test your model in the following section to see if it works correctly.

### 5. Test Your Model

Test on your host machine (needs microphone access):
Expand Down
2 changes: 2 additions & 0 deletions docker-compose.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
services:
kokoro:
image: ghcr.io/remsky/kokoro-fastapi-gpu:latest
ipc: "host"
ports:
- "8880:8880"
deploy:
Expand All @@ -13,6 +14,7 @@ services:

trainer:
build: .
ipc: "host"
deploy:
resources:
reservations:
Expand Down
1 change: 1 addition & 0 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ acoustics==0.2.6
pronouncing==0.2.0
datasets==2.14.6
deep-phonemizer==0.0.19
protobuf>=3.20.0,<4.0.0

# Data download/processing
piper-phonemize
Expand Down
2 changes: 1 addition & 1 deletion setup-data.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ if [ ! -d "$DATA_DIR/audioset_16k" ]; then
echo "Downloading AudioSet background audio..."
mkdir -p "$DATA_DIR/audioset" "$DATA_DIR/audioset_16k"
curl -L -o "$DATA_DIR/audioset/bal_train09.tar" \
'https://huggingface.co/datasets/agkphysics/AudioSet/resolve/main/bal_train09.tar'
'https://huggingface.co/datasets/agkphysics/AudioSet/resolve/728fffe80088808b49db5aa700f2e264c035c880/data/bal_train09.tar'
tar -xf "$DATA_DIR/audioset/bal_train09.tar" -C "$DATA_DIR/audioset"

python3 << EOF
Expand Down