+1
f92d84fcf9
f92d84fcf9
Signed-off-by: tzhouam <tzhouam@connect.ust.hk> Signed-off-by: ZhengWG <zwg0606@gmail.com> Signed-off-by: david6666666 <530634352@qq.com> Signed-off-by: Yueqian Lin <linyueqian@outlook.com> Signed-off-by: nainiu258 <cperfect02@163.com> Signed-off-by: nainiu258 <101917677+nainiu258@users.noreply.github.com> Signed-off-by: JasonJ2021 <jasonj@zju.edu.cn> Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk> Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com> Co-authored-by: skf <54565339+skf-1999@users.noreply.github.com> Co-authored-by: Zheng Wengang <zwg0606@gmail.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com> Co-authored-by: SYLAR <125541396+lishunyang12@users.noreply.github.com> Co-authored-by: Yueqian Lin <linyueqian@outlook.com> Co-authored-by: nainiu258 <101917677+nainiu258@users.noreply.github.com> Co-authored-by: Jason <72191212+JasonJ2021@users.noreply.github.com> Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
46 lines
1.4 KiB
YAML
46 lines
1.4 KiB
YAML
# Universal TTS benchmark model registry.
|
|
# Maps HuggingFace model ID → supported tasks + per-task extra body fields.
|
|
# To add a new TTS model: add an entry here. No code changes required.
|
|
#
|
|
# The server auto-loads its Deploy YAML from vllm_omni/deploy/<model>.yaml via
|
|
# the Pipeline + Deploy schema introduced in #2383, so no stage_config path
|
|
# is tracked here.
|
|
|
|
models:
|
|
# -CustomVoice checkpoints lack speaker_encoder weights, so voice_clone is
|
|
# NOT supported (an attempt raises ValueError from _extract_speaker_embedding
|
|
# at model runtime). Use -Base for voice_clone.
|
|
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice:
|
|
supported_tasks: [default_voice, voice_design]
|
|
backend: openai-audio-speech
|
|
endpoint: /v1/audio/speech
|
|
trust_remote_code: true
|
|
task_extra_body:
|
|
default_voice:
|
|
voice: Vivian
|
|
language: English
|
|
task_type: CustomVoice
|
|
voice_design:
|
|
task_type: VoiceDesign
|
|
language: English
|
|
|
|
Qwen/Qwen3-TTS-12Hz-1.7B-Base:
|
|
supported_tasks: [voice_clone]
|
|
backend: openai-audio-speech
|
|
endpoint: /v1/audio/speech
|
|
trust_remote_code: true
|
|
task_extra_body:
|
|
voice_clone:
|
|
task_type: Base
|
|
|
|
openbmb/VoxCPM2:
|
|
supported_tasks: [voice_clone, default_voice]
|
|
trust_remote_code: true
|
|
backend: openai-audio-speech
|
|
endpoint: /v1/audio/speech
|
|
trust_remote_code: true
|
|
task_extra_body:
|
|
voice_clone: {}
|
|
default_voice:
|
|
voice: default
|