Nik Afiq
5238298b55
- Implemented core model components in `modules.py` including various convolutional layers and normalization techniques. - Added transformation functions in `transforms.py` for piecewise rational quadratic transformations. - Created utility functions in `utils.py` for checkpoint management, logging, and hyperparameter handling. - Introduced monotonic alignment functionality with Cython optimization in `monotonic_align`. - Developed a minimal inference server in `server.py` to handle synthesis requests. - Updated requirements to include necessary dependencies for Cython and scipy.
33 lines
1.1 KiB
Docker
33 lines
1.1 KiB
Docker
# Dev/smoke-test image for tts-gateway (Phase 4 of TTS_GATEWAY_PLAN.md).
|
|
# NOT the polished production image - Phase 5 (deferred) decides the final
|
|
# base image/multi-stage layout. This one just needs to prove the pipeline
|
|
# end-to-end: unlike ha-gateway/ai-gateway/discord-bot, tts-gateway needs
|
|
# `ffmpeg` and the `open_jtalk` CLI (+ dictionary + voice) present at
|
|
# runtime, which rules out a distroless base for now.
|
|
FROM golang:1.26-bookworm AS builder
|
|
WORKDIR /workspace
|
|
|
|
COPY go.work go.work.sum ./
|
|
COPY gen/ ./gen/
|
|
COPY ai-gateway/ ./ai-gateway/
|
|
COPY ha-gateway/ ./ha-gateway/
|
|
COPY discord-bot/ ./discord-bot/
|
|
COPY tts-gateway/ ./tts-gateway/
|
|
|
|
WORKDIR /workspace/tts-gateway
|
|
RUN go mod download
|
|
RUN CGO_ENABLED=0 GOOS=linux go build -o /tts-gateway ./cmd/gateway
|
|
|
|
FROM ubuntu:22.04
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
ffmpeg \
|
|
open-jtalk \
|
|
open-jtalk-mecab-naist-jdic \
|
|
hts-voice-nitech-jp-atr503-m001 \
|
|
ca-certificates \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
COPY --from=builder /tts-gateway /tts-gateway
|
|
EXPOSE 50053
|
|
ENTRYPOINT ["/tts-gateway"]
|