Fibonaccimo's picture
|
download
raw
648 Bytes
metadata
license: apache-2.0
tags:
  - audio.cpp
  - gguf
  - TTS
  - tts
  - ASR
  - asr
  - SST
  - sst
  - SEP
  - sep

GGUFs Q8 for audio.cpp ( Audio to text models ) ASR

Qwen ASR 0.6

Qwen ASR 1.7b

Qwen3 ForcedAligner 0.6B ( addon for Qwen ASR 0.6 and 1.7 to obtain timestamps )

Nemotron ASR 3.5

VibeVoice-ASR

Higgs Audio v3 STT


GGUFs Q8 for audio.cpp ( Text to audio models ) TTS

OutieTTS 1.0

GLM-TTS


GGUFs Q8 for audio.cpp ( vocal source separation from the audio source ) SEP

BS-RoFormer

Xet Storage Details

Size:
648 Bytes
·
Xet hash:
5fa3f89b9525bb15ff98aa30f25106fd51920bc7a8599b019991c77eee967ed6

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.