feat: Qwen3-TTS proxy with HIP graph + CPU decoder optimisations

- OpenAI-compatible Flask proxy (POST /audio/speech, GET /models)
- faster-qwen3-tts HIP graph acceleration: GPU LLM at 1.78x RTF
- CPU speech tokenizer decoder: bypasses MIOpen ConvDirectNaiveConvFwd,
  eliminates 4-40s per-request decode overhead
- attn_implementation=sdpa for transformer attention
- AOTRITON env var toggle (off=short sentences, on=long-form/novel chapters)
- HIP_GRAPHS env var toggle (default on)
- Startup warmup with HIP graph capture (~5s)
- CORS support for browser extension requests
- RTF: 0.9-1.5x on AMD RX 7900 XTX (gfx1100, ROCm 6.3)

Performance vs baseline (CPU-only, ~3 min/sentence):
  12c: 3.2s | 44c: 2.7s | 115c: 6.6s
This commit is contained in:
2026-03-25 21:18:42 -07:00
commit d3ca5ab0b2
5 changed files with 627 additions and 0 deletions

288
setup_qwen3_readaloud.sh Executable file
View File

@@ -0,0 +1,288 @@
#!/usr/bin/env bash
set -euo pipefail
# -----------------------------------------------------------------
# Configuration edit only if you need to change defaults
# -----------------------------------------------------------------
HOME_DIR="${HOME:-/home/oc}"
# Preferred Python version for the virtualenv (must be on the system)
PYTHON_VERSION="3.12"
# Fallback Python version if preferred version is not available
FALLBACK_PYTHON_VERSION="3.10"
# Name of the virtualenv directory (will be created under $HOME)
VENV_DIR="${HOME_DIR}/qwen3tts-venv"
# Model to serve the 0.6B CustomVoice model is quick to download
QWEN_MODEL="Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice"
DEMO_PORT=8000 # Gradio demo port
PROXY_PORT=5000 # Flask proxy port
PROJECT_ROOT="$(pwd)" # must be the directory that contains Qwen3-TTS and read-aloud
PROXY_DIR="${PROJECT_ROOT}/qwen3-proxy"
SYSTEMD_USER_DIR="${HOME_DIR}/.config/systemd/user"
# -----------------------------------------------------------------
# Helper functions for pretty output
# -----------------------------------------------------------------
info(){ echo -e "\e[32m[INFO]\e[0m $*"; }
error(){ echo -e "\e[31m[ERROR]\e[0m $*" >&2; }
warning(){ echo -e "\e[33m[WARNING]\e[0m $*" >&2; }
# -----------------------------------------------------------------
# 0⃣ Helper: ensure we have a recent Python interpreter
# ---------------------------------------------------------
detect_python() {
# Try preferred version first
if command -v "python${PYTHON_VERSION}" >/dev/null 2>&1; then
echo "python${PYTHON_VERSION}"
return 0
elif command -v "python${FALLBACK_PYTHON_VERSION}" >/dev/null 2>&1; then
warning "Python ${PYTHON_VERSION} not found, using ${FALLBACK_PYTHON_VERSION} as fallback"
echo "python${FALLBACK_PYTHON_VERSION}"
return 0
elif command -v python3 >/dev/null 2>&1; then
warning "No specific Python version found, using python3 (may not be compatible)"
echo "python3"
return 0
else
error "No Python interpreter found. Please install Python 3.10 or higher."
exit 1
fi
}
PYTHON_BIN=$(detect_python)
# -----------------------------------------------------------------
# 1⃣ Create (or reuse) a virtualenv and install the Python deps
# -----------------------------------------------------------------
if [[ ! -d "${VENV_DIR}" ]]; then
info "Creating virtualenv at ${VENV_DIR}"
if ! "${PYTHON_BIN}" -m venv "${VENV_DIR}"; then
error "Failed to create virtual environment. Check Python installation and permissions."
exit 1
fi
else
info "Virtualenv already exists reusing."
fi
# Activate the env for the remainder of the script
source "${VENV_DIR}/bin/activate"
# Upgrade pip (helps with binary wheels)
info "Upgrading pip…"
if ! pip install -U pip setuptools wheel; then
error "Failed to upgrade pip"
exit 1
fi
# Check if qwen-tts is already installed
if pip show qwen-tts >/dev/null 2>&1; then
info "qwen-tts already installed, upgrading"
pip install -U qwen-tts
else
info "Installing qwen-tts (Python wrapper)…"
if ! pip install qwen-tts; then
error "Failed to install qwen-tts"
exit 1
fi
fi
# -----------------------------------------------------------------
# 2⃣ Prepare the Flask proxy source tree
# ---------------------------------------------------------
mkdir -p "${PROXY_DIR}"
# Create requirements.txt for the proxy
cat > "${PROXY_DIR}/requirements.txt" <<'EOF'
flask
requests
EOF
# Create app.py for the proxy
cat > "${PROXY_DIR}/app.py" <<'PY'
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""Flask proxy for the ReadAloud extension.
It implements the two endpoints that ReadAloud expects and forwards the
actual synthesis request to a locallyrunning Qwen3TTS Gradio demo.
"""
import os, io, base64
from flask import Flask, request, jsonify, abort, send_file
import requests
app = Flask(__name__)
# --------------------------------------------------------------
# Configuration via environment variables (defaults shown)
# --------------------------------------------------------------
GRADIO_URL = os.getenv("GRADIO_URL", "http://127.0.0.1:8000")
# Map the voice name shown in the extension to the internal speaker token
# that the Gradio demo expects. Extend this dict if you want more voices.
SPEAKERS = {
"Vivian": {"voice_name": "Qwen3 Vivian", "lang": "zh-CN"},
"Ryan": {"voice_name": "Qwen3 Ryan", "lang": "en-US"},
# Add other speakers from the Qwen3TTS README if desired
}
@app.route("/read-aloud/list-voices/premium")
def list_voices():
# Return a JSON array: [{"voice_name":…, "lang":…}, …]
return jsonify(list(SPEAKERS.values()))
@app.route("/read-aloud/speak/<lang>/<voice_name>")
def speak(lang, voice_name):
text = request.args.get("q", "")
if not text:
abort(400, "missing query parameter 'q'")
# Find the internal speaker token (caseinsensitive match)
internal = None
for key, val in SPEAKERS.items():
if val["voice_name"].lower() == voice_name.lower():
internal = key
break
if internal is None:
abort(404, f"voice '{voice_name}' not known to proxy")
# Build the payload for the Gradio API the demo expects:
# [text, language, speaker, instruct]
payload = {"data": [text, lang, internal, ""]}
try:
r = requests.post(f"{GRADIO_URL}/api/predict", json=payload, timeout=120)
except Exception as exc:
abort(502, f"cannot reach Gradio server: {exc}")
if r.status_code != 200:
abort(r.status_code, f"Gradio error: {r.text}")
try:
# Gradio returns something like [{"name": "audio.wav", "data": "data:audio/wav;base64,…"}]
data = r.json()["data"][0]["data"]
except Exception:
abort(500, "unexpected Gradio response format")
# Strip possible dataURL prefix
if data.startswith("data:"):
b64 = data.split(",", 1)[1]
else:
b64 = data
wav_bytes = base64.b64decode(b64)
return send_file(io.BytesIO(wav_bytes), mimetype="audio/wav", as_attachment=False, download_name="speech.wav")
if __name__ == "__main__":
# Flask's builtin dev server is fine for a local user service
app.run(host="0.0.0.0", port=int(os.getenv("PROXY_PORT", "5000")), debug=False)
PY
# Install the proxy deps inside the venv
info "Installing Flask proxy dependencies…"
if ! pip install -r "${PROXY_DIR}/requirements.txt"; then
error "Failed to install Flask proxy dependencies"
exit 1
fi
# -----------------------------------------------------------------
# 3⃣ Write the systemd user unit files (they will activate the venv)
# ---------------------------------------------------------
mkdir -p "${SYSTEMD_USER_DIR}"
# ---- qwen3-tts-demo.service ---------------------------------------
cat > "${SYSTEMD_USER_DIR}/qwen3-tts-demo.service" <<'EOF'
[Unit]
Description=Qwen3TTS Gradio demo (CustomVoice model)
After=network-online.target
Wants=network-online.target
[Service]
# Activate the virtualenv created by the install script
Environment=VENV_DIR=${HOME_DIR}/qwen3tts-venv
ExecStart=/bin/bash -c '\
source "${VENV_DIR}/bin/activate" && \
qwen-tts-demo "${QWEN_MODEL}" \
--ip 0.0.0.0 \
--port ${DEMO_PORT} \
--no-ssl-verify \
--share false'
ExecStop=/usr/bin/pkill -f "qwen-tts-demo"
Restart=on-failure
RestartSec=5
StartLimitBurst=5
StartLimitIntervalSec=60
StandardOutput=journal
StandardError=journal
[Install]
WantedBy=default.target
EOF
# ---- qwen3-tts-proxy.service ---------------------------------------
cat > "${SYSTEMD_USER_DIR}/qwen3-tts-proxy.service" <<'EOF'
[Unit]
Description=Flask proxy translating ReadAloud API → Qwen3TTS Gradio demo
After=qwen3-tts-demo.service
Requires=qwen3-tts-demo.service
# Wait up to ~1 minute for the Gradio demo to become reachable before starting.
ExecStartPre=/usr/bin/bash -c '\
for i in {1..30}; do \
if curl -s http://127.0.0.1:${DEMO_PORT}/ >/dev/null 2>&1; then exit 0; fi; \
echo "Waiting for Qwen3TTS demo … ($i)"; sleep 2; \
done; \
echo "Qwen3TTS demo never became reachable aborting proxy start." >&2; exit 1'
[Service]
Environment=VENV_DIR=${HOME_DIR}/qwen3tts-venv
Environment=PROXY_DIR=${PROJECT_ROOT}/qwen3-proxy
Environment=PROXY_PORT=${PROXY_PORT}
Environment=GRADIO_URL=http://127.0.0.1:${DEMO_PORT}
ExecStart=/bin/bash -c '\
source "${VENV_DIR}/bin/activate" && \
cd "${PROXY_DIR}" && \
python app.py --host 0.0.0.0 --port "${PROXY_PORT}"'
ExecStop=/usr/bin/pkill -f "python.*app.py"
Restart=on-failure
RestartSec=5
StartLimitBurst=5
StartLimitIntervalSec=60
StandardOutput=journal
StandardError=journal
[Install]
WantedBy=default.target
EOF
# -----------------------------------------------------------------
# 4⃣ Reload systemd, enable and start the services
# ---------------------------------------------------------
if command -v systemctl >/dev/null 2>&1; then
info "Reloading user systemd daemon…"
systemctl --user daemon-reload || warning "Failed to reload systemd daemon"
info "Enabling & starting the Qwen3TTS demo service…"
if ! systemctl --user enable --now qwen3-tts-demo.service; then
error "Failed to enable/start Qwen3-TTS demo service"
exit 1
fi
info "Enabling & starting the Flask proxy service…"
if ! systemctl --user enable --now qwen3-tts-proxy.service; then
error "Failed to enable/start Flask proxy service"
exit 1
fi
else
warning "systemctl not found. Services not enabled/started automatically. Please enable manually:"
warning " systemctl --user enable --now qwen3-tts-demo.service"
warning " systemctl --user enable --now qwen3-tts-proxy.service"
fi
# -----------------------------------------------------------------
# 5⃣ Final status report & next steps for the extension
# ---------------------------------------------------------
info "Both services should now be active. Verify with:"
info " systemctl --user status qwen3-tts-demo.service"
info " systemctl --user status qwen3-tts-proxy.service"
info "When configuring the ReadAloud extension, set the service URL to:"
info " http://127.0.0.1:${PROXY_PORT}"
info "Setup finished. Enjoy Qwen3TTS in ReadAloud!"