mirror of
https://github.com/denizsafak/abogen.git
synced 2026-07-18 05:40:26 +02:00
JB
6b5255a80d
- Added LLMClient class for handling requests to LLM API, including methods for listing models and generating completions. - Introduced LLMConfiguration dataclass for managing LLM configuration settings. - Created normalization_settings module to manage normalization configurations and environment variable overrides. - Developed JavaScript functionality for the settings interface, including model fetching and preview generation for LLM and normalization. - Enhanced user experience with status messages and error handling in the settings UI.
39 lines
1.7 KiB
Bash
39 lines
1.7 KiB
Bash
# Copy this file to `.env` and customize the paths to match your environment.
|
|
# Relative paths are resolved from the repository root when running locally.
|
|
# Each `*_DIR` value below points to a directory on the host. Docker Compose
|
|
# mounts it into the container at the standard path noted in the comment.
|
|
|
|
# Host directory that stores JSON settings. Mounted to /config in Docker.
|
|
ABOGEN_SETTINGS_DIR=./config
|
|
|
|
# Host directory for rendered audio/subtitle files. Mounted to /data/outputs
|
|
# in Docker.
|
|
ABOGEN_OUTPUT_DIR=./storage/output
|
|
|
|
# Temporary working directory. When running in Docker, keep this inside the
|
|
# mounted data volume (or another writable host path) so non-root users can
|
|
# write to it. Only audio conversion scratch files are staged here by default;
|
|
# other library caches remain inside the container volume. For local
|
|
# (non-Docker) usage, change this to a path that makes sense on your machine or
|
|
# comment it out to fall back to the OS cache directory. Mounted to /data/cache
|
|
# in Docker.
|
|
ABOGEN_TEMP_DIR=./storage/tmp
|
|
|
|
# UID/GID used when running the Docker container. 1000:1000 matches most Linux hosts.
|
|
# Find your current values with:
|
|
# id -u # UID
|
|
# id -g # GID
|
|
ABOGEN_UID=1000
|
|
ABOGEN_GID=1000
|
|
|
|
# Optional: Seed the web UI with working defaults for the LLM-powered
|
|
# text normalization features. Leave these blank to configure everything
|
|
# from the Settings page.
|
|
ABOGEN_LLM_BASE_URL=https://localhost:11434/v1
|
|
ABOGEN_LLM_API_KEY=ollama
|
|
ABOGEN_LLM_MODEL=llama3.1:8b
|
|
ABOGEN_LLM_TIMEOUT=45
|
|
ABOGEN_LLM_CONTEXT_MODE=paragraph
|
|
# For custom prompts, keep the text on a single line or escape newlines.
|
|
#ABOGEN_LLM_PROMPT=You are assisting with audiobook preparation. Rewrite {{sentence}} for narration.
|