feat(gallery): add parakeet-cpp-nemotron-3.5-asr-streaming-0.6b; bump parakeet.cpp pin

Adds the multilingual prompt-conditioned streaming model to the gallery (q8_0
default, OpenMDW-1.1) and bumps the parakeet-cpp backend pin to the parakeet.cpp
commit that ships nemotron support plus batched causal subsampling and the
batched target_lang C-API.

Assisted-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ettore Di Giacinto
2026-06-06 09:04:49 +00:00
parent aa4f43db47
commit a500ce9b3a
2 changed files with 37 additions and 2 deletions

View File

@@ -1,6 +1,6 @@
# parakeet-cpp backend Makefile.
#
# Upstream pin lives below as PARAKEET_VERSION?=843600590f96a31467a5199f827c253f34c110f7
# Upstream pin lives below as PARAKEET_VERSION?=50dfc24b4faa4ee23a1f59401f1d0c87fc4042b0
# (.github/bump_deps.sh) can find and update it - matches the
# whisper.cpp / ds4 / vibevoice-cpp convention.
#
@@ -15,7 +15,7 @@
# That's what the L0 smoke test uses. The default target below does the
# proper clone-at-pin + cmake build so CI doesn't need a side-checkout.
PARAKEET_VERSION?=843600590f96a31467a5199f827c253f34c110f7
PARAKEET_VERSION?=50dfc24b4faa4ee23a1f59401f1d0c87fc4042b0
PARAKEET_REPO?=https://github.com/mudler/parakeet.cpp
GOCMD?=go

View File

@@ -31887,6 +31887,41 @@
- filename: parakeet-cpp/tdt_ctc-1.1b-f16.gguf
uri: huggingface://mudler/parakeet-cpp-gguf/tdt_ctc-1.1b-f16.gguf
sha256: cd53f64eefac2623a12f2f118ef50b56622dc3012f42c815c6adf0d08292f387
- name: parakeet-cpp-nemotron-3.5-asr-streaming-0.6b
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls:
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b
- https://github.com/mudler/parakeet.cpp
description: |
Multilingual (40+ locales), prompt-conditioned, cache-aware streaming FastConformer RNN-T, 0.6B.
Q8_0 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo). Byte-identical to NeMo at
WER 0 offline and streaming, about 2.5x faster than NeMo on CPU with no GPU. Select a language with
the request "language" field (for example en, de, es, ja-JP), or leave it empty for automatic
detection. License OpenMDW-1.1.
license: other
tags:
- parakeet
- parakeet-cpp
- nemotron
- asr
- speech-recognition
- stt
- multilingual
- streaming
- gguf
- ggml
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-nemotron-3.5-asr-streaming-0.6b
parameters:
model: parakeet-cpp/nemotron-3.5-asr-streaming-0.6b-q8_0.gguf
files:
- filename: parakeet-cpp/nemotron-3.5-asr-streaming-0.6b-q8_0.gguf
uri: huggingface://mudler/parakeet-cpp-gguf/nemotron-3.5-asr-streaming-0.6b-q8_0.gguf
sha256: ba2f13eccd4a5245be728f77e6149bd6a4fdcdd133ff2e08ac6005bcef7a99f1
- name: parakeet-crispasr
url: github:mudler/LocalAI/gallery/virtual.yaml@master
urls: