feat(gallery): add Phonon-2.5 parakeet-cpp models (#12896)

* chore(parakeet-cpp): bump parakeet.cpp to load Phonon-2.5 models

Move the pin to the current parakeet.cpp master. It includes the
dense and packed CPU paths for the Phonon-2.5 checkpoints, which the
previous pin cannot load.

After the bump, run `make purge` in backend/go/parakeet-cpp so the
next build clones the new revision.

Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]

* feat(gallery): add Phonon-2.5 parakeet-cpp models

Add the multilingual Phonon-2.5 (25 European languages) and the
English-only Phonon-2.5-English checkpoints as parakeet-cpp entries.
Each comes in four builds: F16, Q8_0, Q4_K and packed. The packed
build runs on the CPU only. The files are in
mudler/parakeet-cpp-gguf, pinned by SHA-256. The weights are
CC-BY-4.0.

The entries need the parakeet.cpp pin from the previous commit.

Assisted-by: Claude:claude-sonnet-5-5 [Claude Code]

---------

Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
mudler-agentandEttore Di Giacinto authored and GitHub committed 2026-10-25 12:05:33 +01:00
1 parent 10adfa9055
commit ecfb591751
3 files changed
+562 -2

No files matched your search

+2 -2
View File
@@ -1,6 +1,6 @@
# parakeet-cpp backend Makefile.
#
# Upstream pin lives below as PARAKEET_VERSION?=5c9b0fbbd8e611d88e47d7e1ebae9bca9b447e8f
# Upstream pin lives below as PARAKEET_VERSION?=43dce03cb3c36849d5e5a504076be3d9bea7b6c4
# (.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?=5c9b0fbbd8e611d88e47d7e1ebae9bca9b447e8f
PARAKEET_VERSION?=43dce03cb3c36849d5e5a504076be3d9bea7b6c4
PARAKEET_REPO?=https://github.com/mudler/parakeet.cpp
GOCMD?=go
+248
View File
@@ -62679,6 +62679,254 @@
name: parakeet-cpp-tdt-0.6b-v3
parameters:
model: parakeet-cpp/tdt-0.6b-v3-f16.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: parakeet-cpp-phonon-2.5-f16
description: |
Phonon 2.5, F16: a multilingual speech recognition model for 25 European languages, by Fermion Research. F16 file, full precision, about 1.4 GB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
files:
- filename: parakeet-cpp/phonon-2.5-f16.gguf
sha256: 6be6fb7928c1732fd8b881aeaa2bb644fc2ff2464e5a88b3d1017fd34a931ee4
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-f16.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-f16
parameters:
model: parakeet-cpp/phonon-2.5-f16.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: parakeet-cpp-phonon-2.5-q8_0
description: |
Phonon 2.5, Q8_0: a multilingual speech recognition model for 25 European languages, by Fermion Research. Q8_0 quantized file, about 940 MB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
files:
- filename: parakeet-cpp/phonon-2.5-q8_0.gguf
sha256: be2955ea73ca36fb84e69d95abbc2de67e06dec7bb45cc3f53db15c1dca8eee8
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-q8_0.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-q8_0
parameters:
model: parakeet-cpp/phonon-2.5-q8_0.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: parakeet-cpp-phonon-2.5-q4_k
description: |
Phonon 2.5, Q4_K: a multilingual speech recognition model for 25 European languages, by Fermion Research. Q4_K quantized file, about 675 MB, the smallest of the regular builds.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
files:
- filename: parakeet-cpp/phonon-2.5-q4_k.gguf
sha256: 1405f0cd3a71260c0029cf7ff73ab2619a383dbc4c21109923605a85886b1c7a
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-q4_k.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-q4_k
parameters:
model: parakeet-cpp/phonon-2.5-q4_k.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: parakeet-cpp-phonon-2.5-packed
description: |
Phonon 2.5, PACKED: a multilingual speech recognition model for 25 European languages, by Fermion Research. Packed weights, about 240 MB, the smallest file. It runs on the CPU only, because the GPU route for packed files is not in this build. For a GPU, use the f16, q8_0 or q4_k entry instead.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
files:
- filename: parakeet-cpp/phonon-2.5-packed.gguf
sha256: f0339284e385c89a73ebc860937f1c1c346311efee6a40d995f8623b2d8cf7a3
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-packed.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-packed
parameters:
model: parakeet-cpp/phonon-2.5-packed.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: parakeet-cpp-phonon-2.5-english-f16
description: |
Phonon 2.5 English, F16: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. F16 file, full precision, about 1.4 GB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5-English
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
files:
- filename: parakeet-cpp/phonon-2.5-english-f16.gguf
sha256: e5556403115bf3941e769ae84e860c7d2e5d9aad89d986438c31a0e688dc417d
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-english-f16.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-english-f16
parameters:
model: parakeet-cpp/phonon-2.5-english-f16.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: parakeet-cpp-phonon-2.5-english-q8_0
description: |
Phonon 2.5 English, Q8_0: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Q8_0 quantized file, about 940 MB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5-English
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
files:
- filename: parakeet-cpp/phonon-2.5-english-q8_0.gguf
sha256: c484f673e7873761a31c38c2629afe0975dfb2025292730febd93f635489ad70
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-english-q8_0.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-english-q8_0
parameters:
model: parakeet-cpp/phonon-2.5-english-q8_0.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: parakeet-cpp-phonon-2.5-english-q4_k
description: |
Phonon 2.5 English, Q4_K: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Q4_K quantized file, about 675 MB, the smallest of the regular builds.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5-English
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
files:
- filename: parakeet-cpp/phonon-2.5-english-q4_k.gguf
sha256: a0f89ff0bacbba1b6a8a8506a31b11e794550ff7290979c4e50cfd38f40d12c8
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-english-q4_k.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-english-q4_k
parameters:
model: parakeet-cpp/phonon-2.5-english-q4_k.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: parakeet-cpp-phonon-2.5-english-packed
description: |
Phonon 2.5 English, PACKED: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Packed weights, about 240 MB, the smallest file. It runs on the CPU only, because the GPU route for packed files is not in this build. For a GPU, use the f16, q8_0 or q4_k entry instead.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5-English
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
files:
- filename: parakeet-cpp/phonon-2.5-english-packed.gguf
sha256: 0ee054a9dfe000884224999e4805c48bfb98343763c08b8133bd401e182a7ab2
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-english-packed.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-english-packed
parameters:
model: parakeet-cpp/phonon-2.5-english-packed.gguf
- url: github:mudler/LocalAI/gallery/virtual.yaml@master
name: orukeet
description: |
+312
View File
@@ -76380,6 +76380,318 @@
name: parakeet-cpp-tdt-0.6b-v3
parameters:
model: parakeet-cpp/tdt-0.6b-v3-f16.gguf
- kind: model
id: parakeet-cpp-phonon-2.5-f16
name: parakeet-cpp-phonon-2.5-f16
version: 0.0.0-gallery.96d38dcc9411
description: |
Phonon 2.5, F16: a multilingual speech recognition model for 25 European languages, by Fermion Research. F16 file, full precision, about 1.4 GB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: parakeet-cpp/phonon-2.5-f16.gguf
sha256: 6be6fb7928c1732fd8b881aeaa2bb644fc2ff2464e5a88b3d1017fd34a931ee4
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-f16.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-f16
parameters:
model: parakeet-cpp/phonon-2.5-f16.gguf
- kind: model
id: parakeet-cpp-phonon-2.5-q8_0
name: parakeet-cpp-phonon-2.5-q8_0
version: 0.0.0-gallery.7b5d2ae0221c
description: |
Phonon 2.5, Q8_0: a multilingual speech recognition model for 25 European languages, by Fermion Research. Q8_0 quantized file, about 940 MB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: parakeet-cpp/phonon-2.5-q8_0.gguf
sha256: be2955ea73ca36fb84e69d95abbc2de67e06dec7bb45cc3f53db15c1dca8eee8
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-q8_0.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-q8_0
parameters:
model: parakeet-cpp/phonon-2.5-q8_0.gguf
- kind: model
id: parakeet-cpp-phonon-2.5-q4_k
name: parakeet-cpp-phonon-2.5-q4_k
version: 0.0.0-gallery.4a90fe10c045
description: |
Phonon 2.5, Q4_K: a multilingual speech recognition model for 25 European languages, by Fermion Research. Q4_K quantized file, about 675 MB, the smallest of the regular builds.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: parakeet-cpp/phonon-2.5-q4_k.gguf
sha256: 1405f0cd3a71260c0029cf7ff73ab2619a383dbc4c21109923605a85886b1c7a
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-q4_k.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-q4_k
parameters:
model: parakeet-cpp/phonon-2.5-q4_k.gguf
- kind: model
id: parakeet-cpp-phonon-2.5-packed
name: parakeet-cpp-phonon-2.5-packed
version: 0.0.0-gallery.c00450d3865f
description: |
Phonon 2.5, PACKED: a multilingual speech recognition model for 25 European languages, by Fermion Research. Packed weights, about 240 MB, the smallest file. It runs on the CPU only, because the GPU route for packed files is not in this build. For a GPU, use the f16, q8_0 or q4_k entry instead.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: parakeet-cpp/phonon-2.5-packed.gguf
sha256: f0339284e385c89a73ebc860937f1c1c346311efee6a40d995f8623b2d8cf7a3
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-packed.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-packed
parameters:
model: parakeet-cpp/phonon-2.5-packed.gguf
- kind: model
id: parakeet-cpp-phonon-2.5-english-f16
name: parakeet-cpp-phonon-2.5-english-f16
version: 0.0.0-gallery.a7ddb3fc530e
description: |
Phonon 2.5 English, F16: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. F16 file, full precision, about 1.4 GB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5-English
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: parakeet-cpp/phonon-2.5-english-f16.gguf
sha256: e5556403115bf3941e769ae84e860c7d2e5d9aad89d986438c31a0e688dc417d
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-english-f16.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-english-f16
parameters:
model: parakeet-cpp/phonon-2.5-english-f16.gguf
- kind: model
id: parakeet-cpp-phonon-2.5-english-q8_0
name: parakeet-cpp-phonon-2.5-english-q8_0
version: 0.0.0-gallery.4ee22fed2915
description: |
Phonon 2.5 English, Q8_0: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Q8_0 quantized file, about 940 MB.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5-English
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: parakeet-cpp/phonon-2.5-english-q8_0.gguf
sha256: c484f673e7873761a31c38c2629afe0975dfb2025292730febd93f635489ad70
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-english-q8_0.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-english-q8_0
parameters:
model: parakeet-cpp/phonon-2.5-english-q8_0.gguf
- kind: model
id: parakeet-cpp-phonon-2.5-english-q4_k
name: parakeet-cpp-phonon-2.5-english-q4_k
version: 0.0.0-gallery.763a34bb5387
description: |
Phonon 2.5 English, Q4_K: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Q4_K quantized file, about 675 MB, the smallest of the regular builds.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5-English
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: parakeet-cpp/phonon-2.5-english-q4_k.gguf
sha256: a0f89ff0bacbba1b6a8a8506a31b11e794550ff7290979c4e50cfd38f40d12c8
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-english-q4_k.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-english-q4_k
parameters:
model: parakeet-cpp/phonon-2.5-english-q4_k.gguf
- kind: model
id: parakeet-cpp-phonon-2.5-english-packed
name: parakeet-cpp-phonon-2.5-english-packed
version: 0.0.0-gallery.4b9184a6bc29
description: |
Phonon 2.5 English, PACKED: the English-only speech recognition model of the Phonon 2.5 family, by Fermion Research. Packed weights, about 240 MB, the smallest file. It runs on the CPU only, because the GPU route for packed files is not in this build. For a GPU, use the f16, q8_0 or q4_k entry instead.
GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet). The
weights are released under CC-BY-4.0: credit Fermion Research.
license: cc-by-4.0
urls:
- https://huggingface.co/FermionResearch/Phonon-2.5-English
- https://huggingface.co/mudler/parakeet-cpp-gguf
- https://github.com/mudler/parakeet.cpp
tags:
- parakeet
- parakeet-cpp
- phonon
- asr
- speech-recognition
- stt
- gguf
- ggml
channel: gallery
policy:
requireSignature: false
schemaVersion: 1
model:
url: github:mudler/LocalAI/gallery/virtual.yaml@master
files:
- filename: parakeet-cpp/phonon-2.5-english-packed.gguf
sha256: 0ee054a9dfe000884224999e4805c48bfb98343763c08b8133bd401e182a7ab2
uri: huggingface://mudler/parakeet-cpp-gguf/phonon-2.5-english-packed.gguf
overrides:
backend: parakeet-cpp
known_usecases:
- transcript
name: parakeet-cpp-phonon-2.5-english-packed
parameters:
model: parakeet-cpp/phonon-2.5-english-packed.gguf
- kind: model
id: orukeet
name: orukeet