Compare model versions
Earlier snapshot
Snapshot #5291
Repository revision
bd27c7e (opens in a new tab)
Recorded at 04 Oct 2026, 09:16 UTC
Unchanged through 16 Oct 2026, 06:43 UTC
Later snapshot
Snapshot #6264
Repository revision
c1a2a07 (opens in a new tab)
Recorded at 16 Oct 2026, 09:31 UTC
Unchanged through 05 Nov 2026, 08:28 UTC
Summary
Licence
ChangedDeclared licence unchanged. Licence file content changed.
CC-BY-4.0
CC-BY-4.0
| File | Status | Before | After |
|---|---|---|---|
LICENSE |
ADDED | — |
Git blob ID da6ab6cc8f333d7e89a99812866df8f24374d47c
18.7 KB
|
PinDiff reports the declared licence and licence files. It does not interpret licence terms.
Weights
UnchangedNo change
Remote code / configuration
UnchangedNo change
Remote code
No
No
Access / gating
UnchangedNo change
Public
Public
Model card
ChangedModel card modified (2 sections)
License Changed Material section +4 −0
Diff
Inherited from the base model: **CC-BY-4.0**. See the
[upstream model card](https://huggingface.co/nvidia/canary-1b-flash) for full terms.
Added: + This repository includes the license text
Added: + ([`LICENSE`](https://huggingface.co/handy-computer/canary-1b-flash-gguf/blob/main/LICENSE)) and a
Added: + [`NOTICE`](https://huggingface.co/handy-computer/canary-1b-flash-gguf/blob/main/NOTICE) recording
Added: + how these files were derived from the original.
---
Before
Inherited from the base model: **CC-BY-4.0**. See the [upstream model card](https://huggingface.co/nvidia/canary-1b-flash) for full terms. ---
After
Inherited from the base model: **CC-BY-4.0**. See the [upstream model card](https://huggingface.co/nvidia/canary-1b-flash) for full terms. This repository includes the license text ([`LICENSE`](https://huggingface.co/handy-computer/canary-1b-flash-gguf/blob/main/LICENSE)) and a [`NOTICE`](https://huggingface.co/handy-computer/canary-1b-flash-gguf/blob/main/NOTICE) recording how these files were derived from the original. ---
canary-1b-flash: transcribe.cpp GGUF Changed +6 −8
Diff
⋯ 7 unchanged lines
[db53eda](https://github.com/handy-computer/transcribe.cpp/tree/db53eda)
on 2026-05-08.
Removed: - Offline multilingual speech-to-text and translation. An 883M-parameter
Removed: - multitask AED with a 32-layer FastConformer encoder and a 4-layer
Removed: - Transformer decoder. Supports automatic speech recognition in English,
Removed: - German, Spanish, and French, and bidirectional EN↔{DE, ES, FR}
Removed: - translation. Takes a
Removed: - 16 kHz mono WAV and produces a transcript. Not a streaming model;
Removed: - word/segment timestamps are upstream-experimental and not exposed in
Removed: - the v1 port.
Added: + Offline multilingual speech-to-text and translation. A multitask AED
Added: + with a 32-layer FastConformer encoder and a 4-layer Transformer decoder.
Added: + Supports automatic speech recognition in English, German, Spanish, and
Added: + French, and bidirectional EN↔{DE, ES, FR} translation. Takes a 16 kHz
Added: + mono WAV and produces a transcript. Not a streaming model; word/segment
Added: + timestamps are upstream-experimental and not exposed in the v1 port.
Before
GGUF conversions of [nvidia/canary-1b-flash](https://huggingface.co/nvidia/canary-1b-flash) for use
with [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).
Ported from upstream commit
[a9a55e0](https://huggingface.co/nvidia/canary-1b-flash/commit/a9a55e0),
pinned 2026-05-08.
Validated against the NeMo reference at transcribe.cpp commit
[db53eda](https://github.com/handy-computer/transcribe.cpp/tree/db53eda)
on 2026-05-08.
Offline multilingual speech-to-text and translation. An 883M-parameter
multitask AED with a 32-layer FastConformer encoder and a 4-layer
Transformer decoder. Supports automatic speech recognition in English,
German, Spanish, and French, and bidirectional EN↔{DE, ES, FR}
translation. Takes a
16 kHz mono WAV and produces a transcript. Not a streaming model;
word/segment timestamps are upstream-experimental and not exposed in
the v1 port.
After
GGUF conversions of [nvidia/canary-1b-flash](https://huggingface.co/nvidia/canary-1b-flash) for use
with [transcribe.cpp](https://github.com/handy-computer/transcribe.cpp).
Ported from upstream commit
[a9a55e0](https://huggingface.co/nvidia/canary-1b-flash/commit/a9a55e0),
pinned 2026-05-08.
Validated against the NeMo reference at transcribe.cpp commit
[db53eda](https://github.com/handy-computer/transcribe.cpp/tree/db53eda)
on 2026-05-08.
Offline multilingual speech-to-text and translation. A multitask AED
with a 32-layer FastConformer encoder and a 4-layer Transformer decoder.
Supports automatic speech recognition in English, German, Spanish, and
French, and bidirectional EN↔{DE, ES, FR} translation. Takes a 16 kHz
mono WAV and produces a transcript. Not a streaming model; word/segment
timestamps are upstream-experimental and not exposed in the v1 port.
39 other sections unchanged.
Repository status
ChangedRepository revision moved
- Earlier
-
Revision
bd27c7e(opens in a new tab) · 8 files · 8.70 GB - Later
-
Revision
c1a2a07(opens in a new tab) · 10 files · 8.70 GB
A new revision does not by itself mean files changed; the categories above show what differs.
Files
Changed1 other file changed
1 added
| File | Status | Before | After |
|---|---|---|---|
NOTICE |
ADDED | — |
Git blob ID 4b529bda44ac49360724ef55cc977b70093cd07e
395 B
|
Evidence observed by PinDiff from the Hugging Face API and stored when recorded. PinDiff compares stored metadata, hashes and text files; it does not download weight files. Change events recorded between these snapshots