Add crediting block, oruk.ai links, questions pointer and FLEURS model-index

README: a 'Crediting Orukeet' copy-paste block (Orukeet by Oruk, built on Parakeet-TDT v3; weights on Hugging Face; CC BY-SA 4.0; https://oruk.ai/models/orukeet), oruk.ai links tagged utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet, a 'Questions and bugs' pointer (GitHub issues for bugs, Discussions for model questions; no language-forcing control; hosted Orukeet is English-only), and the license sentence 'Code is MIT; weights and fitted kernels are CC BY-SA 4.0' linking LICENSE and LICENSE-WEIGHTS. Front matter: a model-index with FLEURS only (pooled 25-language 9.85% and English 3.82% WER from the card's own table); LibriSpeech test-other is excluded because it was used for adaptation. No hosted-API section: the origin probe timed out and /readyz does not list Orukeet. From the 2026-11-10 STT audit, section 8 (F047, F157, F147, G2604, G2702, G1301, G1308). Mirrors Oruk-AI/orukeet PR #12.

README.md

@@ -11,6 +11,32 @@ transcribe_cpp:
   lang_detect: true
   timestamps: token
 tags: [parakeet, tdt, onnx, sherpa-onnx, gguf, multilingual, speech-recognition, gabor, fastconformer]
+model-index:
+- name: oruk/orukeet
+  results:
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: FLEURS (25 languages, pooled)
+      type: google/fleurs
+      split: test
+    metrics:
+    - type: wer
+      value: 9.85
+      name: Pooled test WER, 20,146 recordings
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: FLEURS English
+      type: google/fleurs
+      config: en_us
+      split: test
+    metrics:
+    - type: wer
+      value: 3.82
+      name: Test WER, 647 recordings
 ---
 
 <!-- orukeet-brand:start -->
@@ -43,7 +69,7 @@ Orukeet outperforms Parakeet on **61 of 74 tested splits**, including LibriSpeec
 
 Use Orukeet for recordings, media, batch transcription, server workers and interactive applications. NeMo, ONNX INT8, native Q8 and native F16 all derive from the same **r3 release checkpoint** (`031c8ddab484`).
 
-[Code](https://github.com/Oruk-AI/orukeet) · [OpenWhispr PR](https://github.com/OpenWhispr/openwhispr/pull/2085) · [Technical report](orukeet-technical-report.pdf) · [Artifact hashes](ARTIFACTS.json)
+[Code](https://github.com/Oruk-AI/orukeet) · [OpenWhispr PR](https://github.com/OpenWhispr/openwhispr/pull/2085) · [Technical report](orukeet-technical-report.pdf) · [Artifact hashes](ARTIFACTS.json) · [Orukeet at oruk.ai](https://oruk.ai/models/orukeet?utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet) · [Oruk speech-to-text API](https://oruk.ai/speech-to-text-api?utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet)
 
 ## Run Orukeet with Transformers
 
@@ -195,9 +221,25 @@ Q8 and F16 pass real transcription and protocol checks on Apple silicon with Met
 
 [Artifact catalog](https://github.com/Oruk-AI/orukeet/blob/main/src/orukeet/artifacts.json) · [Native conversion and validation](https://github.com/Oruk-AI/orukeet/tree/main/evidence/r3-promotion-20260908/)
 
+## Questions and bugs
+
+Reproducible transcription or runtime bugs go to [GitHub issues](https://github.com/Oruk-AI/orukeet/issues/new/choose); include the model SHA-256, OS/architecture, runtime/device and input format. Model-level questions (languages, accuracy, fine-tuning, licensing, packaging Orukeet in an app) go to [GitHub Discussions](https://github.com/Oruk-AI/orukeet/discussions). Orukeet detects the language itself: the weights and the native API have no language-forcing or vocabulary-biasing input, and the native response returns `language: null`. Hosted Orukeet on oruk.ai transcribes English only. Security reports: [SECURITY.md](https://github.com/Oruk-AI/orukeet/blob/main/SECURITY.md).
+
+## Crediting Orukeet
+
+If you ship, repackage, benchmark or write about Orukeet, credit it by name and origin. Copy and paste:
+
+> Orukeet by Oruk, built on Parakeet-TDT v3; weights on Hugging Face; CC BY-SA 4.0. https://oruk.ai/models/orukeet
+
+```markdown
+[Orukeet](https://oruk.ai/models/orukeet) by [Oruk](https://oruk.ai), built on NVIDIA Parakeet-TDT v3; weights on [Hugging Face](https://huggingface.co/oruk/orukeet) under CC BY-SA 4.0.
+```
+
+Redistributed weights keep NVIDIA's Parakeet attribution and the CC BY-SA 4.0 notice ([NOTICE.md](NOTICE.md)). For papers, use the citation below.
+
 ## License and attribution
 
-Code: MIT. Weights and fitted kernels: CC BY-SA 4.0, retaining NVIDIA's foundation attribution. Transcript-free metric records: CC BY 4.0. Dataset audio is obtained from its original providers under their terms.
+Code is MIT ([LICENSE](LICENSE)); weights and fitted kernels are CC BY-SA 4.0 ([LICENSE-WEIGHTS](LICENSE-WEIGHTS)), retaining NVIDIA's foundation attribution. Transcript-free metric records: CC BY 4.0. Dataset audio is obtained from its original providers under their terms.
 
 [Data provenance](https://github.com/Oruk-AI/orukeet/blob/main/docs/data-and-licenses.md) · [Attribution](NOTICE.md)