Add Hviske v6 BF16 and Q8_0 models

.gitattributes

@@ -136,3 +136,5 @@ Breeze-TTS-2-GGUF/breeze-tts-2-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
 TF-GridNet-GGUF/tf-gridnet-wsj0-2mix-f32.gguf filter=lfs diff=lfs merge=lfs -text
 MossFormer2-GGUF/mossformer2-ss-16k-f16.gguf filter=lfs diff=lfs merge=lfs -text
 MossFormer2-GGUF/mossformer2-ss-16k-f32.gguf filter=lfs diff=lfs merge=lfs -text
+Hviske-v6-GGUF/hviske-v6-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+Hviske-v6-GGUF/hviske-v6-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Hviske-v6-GGUF/LICENSES/Apache-2.0.txt

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Hviske-v6-GGUF/LICENSES/MIT-Whisper.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2022 OpenAI
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Hviske-v6-GGUF/NOTICE

@@ -0,0 +1,51 @@
+hviske-v6
+Copyright (c) 2026 Syv.ai
+
+The Python modelling, configuration and inference code in this repository is a
+DERIVATIVE WORK of saga-2 by Capacit A/S:
+
+    saga-2
+    Copyright (c) 2026 Capacit A/S
+    https://huggingface.co/capacit-ai/saga-2-m
+
+It was derived from a revision published under the Apache License, Version 2.0
+(the licence saga-2 carried up to and including commit
+f1c014f383d59be1302c4eac350f6335a30b8f68; saga-2 moved to CC BY-NC 4.0 for
+revisions published from 2026-09-24). A copy of the Apache License is in
+LICENSES/Apache-2.0.txt.
+
+Files derived from saga-2, and what they were derived from:
+
+    modeling_whisper_qwen.py      saga2/model.py, saga2/encoder_pos.py
+    configuration_whisper_qwen.py saga2/model.py (WQwenConfig)
+    processing_whisper_qwen.py    saga2/gpu_mel.py, saga2/decode.py
+    vllm/hviske_vllm/encoder.py   saga2/encoder_pos.py
+    vllm/hviske_vllm/audio.py     saga2/gpu_mel.py, saga2/decode.py
+
+All of these files have been modified. The changes are summarised at the top of
+each file, as Apache License 2.0 section 4(b) requires.
+
+The model WEIGHTS in this repository are also a derivative work of saga-2. The
+encoder was initialised from the encoder tensors of the first release of
+capacit-ai/saga-2-m -- published under the Apache License, Version 2.0 -- and was
+then trained further on the corpus described in the model card. The decoder was
+initialised from Qwen/Qwen3-0.6B-Base and the projector was randomly initialised;
+those two parts are not derived from saga-2.
+
+Modification, per Apache License 2.0 section 4(b): the saga-2 encoder weights have
+been changed by further training. The RoPE adaptation of the Whisper encoder and
+the Danish training preceding this repository are Capacit A/S's work.
+
+This repository's own weights are licensed CC BY-NC 4.0; see the model card.
+
+Third-party components
+----------------------
+Encoder: capacit-ai/saga-2-m, Copyright (c) 2026 Capacit A/S, Apache License 2.0
+  (the licence carried by the revision this was derived from). See
+  LICENSES/Apache-2.0.txt. saga-2-m is in turn derived from
+  openai/whisper-large-v3-turbo, Copyright (c) 2022 OpenAI, MIT License. See
+  LICENSES/MIT-Whisper.txt.
+Decoder: Qwen/Qwen3-0.6B-Base, Copyright 2024 Alibaba Cloud,
+  Apache License 2.0. See LICENSES/Apache-2.0.txt.
+
+Training corpora carry their own licenses.

Hviske-v6-GGUF/README.md

@@ -0,0 +1,133 @@
+---
+license: cc-by-nc-4.0
+language:
+- da
+pipeline_tag: automatic-speech-recognition
+tags:
+- audio.cpp
+- gguf
+- whisper
+- qwen3
+base_model:
+- syvai/hviske-v6
+---
+
+# Hviske v6 GGUF
+
+For use with [audio.cpp](https://github.com/0xShug0/audio.cpp), family
+`hviske_asr_v6`. These self-contained packages include the tokenizer, configuration,
+and model spec; no separate Python runtime or tokenizer download is required.
+
+Converted from [syvai/hviske-v6](https://huggingface.co/syvai/hviske-v6/tree/323b5ffdf54ef22196340a0b37cb11e668fefc5a),
+revision `323b5ffdf54ef22196340a0b37cb11e668fefc5a`.
+The architecture is a rotary-position Whisper encoder, frame-stacking projector,
+and Qwen3 decoder. It is separate from the Conformer-based Hviske v5 family.
+
+## Packages
+
+| File | Storage | Size | Recommendation |
+|---|---|---:|---|
+| `hviske-v6-bf16.gguf` | Native BF16 | 2.61 GiB | Default; preserves source tensor precision. |
+| `hviske-v6-q8_0.gguf` | Q8_0 | 1.54 GiB | Lower memory use, with expected transcript drift. |
+
+The model transcribes Danish. It supports offline longform transcription with
+silence-based splitting, but does not provide timestamps, diarization, or native
+streaming. CUDA, Vulkan, and CPU were tested.
+
+```bash
+audiocpp_cli --task asr --family hviske_asr_v6 \
+  --model /path/to/hviske-v6-bf16.gguf --backend cuda \
+  --audio danish.wav --threads 8 --log
+```
+
+Formatting controls require both `cased` and `punctuated`, for example
+`--request-option cased=true --request-option punctuated=true`.
+The default uses two beams; `--request-option num_beams=1` selects greedy decoding.
+See the [model documentation](https://github.com/0xShug0/audio.cpp/blob/main/docs/models/hviske_asr_v6.md)
+for all options and conversion instructions.
+
+## CUDA Performance
+
+RTX 5090, eight CPU threads, Debug C++ build. Each process first transcribed a
+16.15-second warmup clip, then a 180-second real Danish recording. Model loading
+is excluded from inference time. Peak VRAM is process-scoped NVML sampling at
+20-ms intervals across the request sequence, not retained memory.
+
+Python used the official wrapper with its defaults, including BF16 on CUDA,
+two beams, and longform batch size eight. C++ used native package storage and
+the same default two-beam policy. No TF32 or precision overrides were used for
+these performance measurements. These are individual warmed measurements, not
+a statistical benchmark.
+
+| Runtime | Warm 180-s inference | RTF | Observed peak VRAM |
+|---|---:|---:|---:|
+| Official Python (BF16 default) | 2.774 s | 0.01541 | 4,260 MiB |
+| C++ BF16 | 2.239 s | 0.01244 | 3,198 MiB |
+| C++ Q8_0 | 2.014 s | 0.01119 | 2,246 MiB |
+
+C++ BF16 is 1.24x faster in this comparison, with about 25% lower peak VRAM.
+An earlier Python run took 2.641 s, against which C++ BF16 is 1.18x faster.
+The same-dtype improvement does not depend on quantization: writing prefill K/V
+directly into the backend cache removed a CPU export/import round trip and reduced
+C++ BF16 inference from 2.800 s to 2.398 s without changing its transcripts.
+Packing Q/K/V and gate/up projections and reusing the host logits buffer further
+reduced it to 2.239 s. These use the same framework modules on all backends,
+without backend-specific gates or changing weight precision.
+Q8 is an optional storage/memory trade-off, not evidence for the BF16 optimization.
+Python was PyTorch 2.11.0+cu128 with Transformers 4.57.6. The upstream custom
+model code did not load with Transformers 5.12.1 in this validation.
+
+The longform input was the first 180 seconds of
+[Da-Solen.ogg](https://commons.wikimedia.org/wiki/File:Da-Solen.ogg), read by
+Danielle dk, licensed [CC BY-SA 3.0](https://creativecommons.org/licenses/by-sa/3.0/),
+converted to mono 16-kHz PCM16. It contains no synthesized or repeated segments.
+
+## CPU Performance
+
+AMD Ryzen 9 7900X, eight threads in both implementations. Python used its default
+FP32 CPU weights; C++ used `hviske_asr_v6.weight_type=f32` for the same precision.
+The request sequence was a short warmup, the same 180-second recording, then the
+short recording again. Python batches longform chunks by default; C++ processes
+them sequentially. Times exclude loading, and each row is a single warmed request.
+
+| Input | C++ | Official Python | C++ RTF | Python RTF |
+|---|---:|---:|---:|---:|
+| 16.15 seconds | 4.962 s | 8.434 s | 0.307 | 0.522 |
+| 180 seconds | 54.988 s | 110.282 s | 0.305 | 0.613 |
+
+Short transcripts match exactly. On longform, Python CPU and C++ FP32 differ on
+`stof` versus `støv` and four words in the repeated ending. These differences were
+already present before projection packing; the optimization preserves C++ output.
+Its additional CPU gain is modest: 56.352 s to 54.988 s on longform.
+
+## Parity and Limitations
+
+Controlled parity was tested separately: Python FP32 versus C++ with
+`hviske_asr_v6.weight_type=f32`, both with `NVIDIA_TF32_OVERRIDE=0`.
+All three short Danish recordings produced identical transcripts. This is
+transcript parity, not a claim of bit-identical intermediate tensors.
+
+With normal runtime settings, BF16 CUDA and CPU differ from Python on one phrase
+in one short recording: Python emits `reachdirektivet`, while C++ emits
+`reighedsdirektivet og`. Vulkan BF16 and Q8 CPU match Python on this recording.
+The controlled FP32 comparison removes this difference; disabling TF32 alone does
+not. Backend and weight precision can affect beam selection.
+
+On the 180-second recording, BF16 C++ has zero normalized word differences from
+Python's 352-word transcript, with punctuation/casing differences. Q8 has two
+word substitutions relative to Python (0.57% transcript disagreement):
+`wikpedia` becomes `wikipedia`, and `støv` becomes `stod`. This is not WER
+against a human ground-truth transcript. Normalization uses lowercase Unicode
+word tokens, ignoring punctuation. Q8 output changed slightly with projection
+packing; BF16 output and controlled FP32 parity remained unchanged.
+
+Formatting controls, greedy decoding, changing inputs, and repeat requests were
+tested. The short request after longform retains its original transcript. Model
+quality remains upstream-dependent; the Python output itself repeats part of the
+last sentence in this excerpt.
+
+## License
+
+The weights are CC BY-NC 4.0, not licensed for commercial use. Preserve the
+upstream `NOTICE` and `LICENSES/` files, which describe the underlying Saga-2,
+Whisper, and Qwen components and their notices.

Hviske-v6-GGUF/hviske-v6-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9af75b8e9d643fb8b078ebb847719b696892cd1e9bd088290fc3e817b9b218
+size 2803839072

Hviske-v6-GGUF/hviske-v6-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04530800bc2bb9ed63f3011f6eaba3d33df9577ef40481740d932d22c94f7521
+size 1650364512