diff options
Diffstat (limited to 'converter/config.py')
| -rw-r--r-- | converter/config.py | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/converter/config.py b/converter/config.py index f795520..efec0dd 100644 --- a/converter/config.py +++ b/converter/config.py @@ -108,6 +108,28 @@ VOICE_CLONE_SEED = -1 VOICE_CLONE_API_URL = "http://127.0.0.1:7861" # ============================================================================= +# FASTER TTS SETTINGS (optional --faster backend) +# ============================================================================= +# --faster talks to the OpenAI-compatible server from faster-qwen3-tts +# (examples/openai_server.py) instead of the qwen-tts Gradio demos. The +# reference voice (ref audio, ref text) and language are configured on the +# SERVER side (--ref-audio/--ref-text or a --voices JSON file); the converter +# only sends text. See the "Faster backend" section of the README. + +FASTER_TTS_API_URL = "http://127.0.0.1:8000" +# Voice entry to request. MUST match a key in the server's voices.json (or +# "default" when the server was launched with --ref-audio). NOTE: the stock +# server silently falls back to its first configured voice when the requested +# name is unknown, so a mismatch here is easy to miss. +FASTER_TTS_VOICE = "default" +FASTER_TTS_SAMPLE_RATE = 24000 # Qwen3-TTS 12Hz codec output rate +# The Gradio demo sub-chunked text server-side (~200 chars); the faster server +# takes one generation per request, so long chunks are sub-chunked client-side. +FASTER_SUBCHUNK_WORDS = 40 # ~200 chars per request +FASTER_HTTP_TIMEOUT = 300 # Seconds before a speech request times out +FASTER_SUBCHUNK_RETRIES = 3 # Attempts per sub-chunk request + +# ============================================================================= # PROCESSING SETTINGS # ============================================================================= |