mirror of
https://github.com/mudler/LocalAI.git
synced 2026-04-04 15:04:27 -04:00
chore(model gallery): add voxcpm, whisperx, moonshine-tiny (#8534)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
committed by
GitHub
parent
8616397d59
commit
088205339c
@@ -52,6 +52,66 @@
|
||||
- filename: voxtral-model/tekken.json
|
||||
uri: https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602/resolve/main/tekken.json
|
||||
sha256: 8434af1d39eba99f0ef46cf1450bf1a63fa941a26933a1ef5dbbf4adf0d00e44
|
||||
- name: moonshine-tiny
|
||||
license: apache-2.0
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
description: |
|
||||
Moonshine Tiny is a lightweight speech-to-text model optimized for fast transcription. It is designed for efficient on-device ASR with high accuracy relative to its size.
|
||||
urls:
|
||||
- https://github.com/moonshine-ai/moonshine
|
||||
tags:
|
||||
- stt
|
||||
- speech-to-text
|
||||
- asr
|
||||
- audio-transcription
|
||||
- cpu
|
||||
- gpu
|
||||
overrides:
|
||||
backend: moonshine
|
||||
known_usecases:
|
||||
- transcript
|
||||
parameters:
|
||||
model: moonshine/tiny
|
||||
- name: whisperx-tiny
|
||||
license: mit
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
description: |
|
||||
WhisperX Tiny is a fast and accurate speech recognition model with speaker diarization capabilities. Built on OpenAI's Whisper with additional features for alignment and speaker segmentation.
|
||||
urls:
|
||||
- https://github.com/m-bain/whisperX
|
||||
tags:
|
||||
- stt
|
||||
- speech-to-text
|
||||
- asr
|
||||
- audio-transcription
|
||||
- speaker-diarization
|
||||
- cpu
|
||||
- gpu
|
||||
overrides:
|
||||
backend: whisperx
|
||||
known_usecases:
|
||||
- transcript
|
||||
parameters:
|
||||
model: tiny
|
||||
- name: voxcpm-1.5
|
||||
license: apache-2.0
|
||||
url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
|
||||
description: |
|
||||
VoxCPM 1.5 is an end-to-end text-to-speech (TTS) model from ModelBest. It features zero-shot voice cloning and high-quality speech synthesis capabilities.
|
||||
urls:
|
||||
- https://huggingface.co/openbmb/VoxCPM1.5
|
||||
tags:
|
||||
- tts
|
||||
- text-to-speech
|
||||
- voice-cloning
|
||||
- cpu
|
||||
- gpu
|
||||
overrides:
|
||||
backend: voxcpm
|
||||
known_usecases:
|
||||
- tts
|
||||
parameters:
|
||||
model: openbmb/VoxCPM1.5
|
||||
- name: "ace-step-turbo"
|
||||
license: mit
|
||||
tags:
|
||||
|
||||
Reference in New Issue
Block a user