Automatic Speech Recognition
NeMo
ONNX
Safetensors
GGUF
parakeet_tdt
parakeet
tdt
sherpa-onnx
multilingual
speech-recognition
gabor
fastconformer
Eval Results (legacy)
Instructions to use oruk/orukeet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use oruk/orukeet with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("oruk/orukeet") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Add the Hosted API section (English, 60 s, 4 MiB, no word timestamps, plan allowance)
Browse filesDiscloses the hosted preview's limits from the oruk.ai OpenAPI contract and what hosted adds over the local weights (no install or GPU, optional emotion scores and speaker diarization). Links carry utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet. Everything else on the card is unchanged.
README.md
CHANGED
|
@@ -221,6 +221,10 @@ Q8 and F16 pass real transcription and protocol checks on Apple silicon with Met
|
|
| 221 |
|
| 222 |
[Artifact catalog](https://github.com/Oruk-AI/orukeet/blob/main/src/orukeet/artifacts.json) 路 [Native conversion and validation](https://github.com/Oruk-AI/orukeet/tree/main/evidence/r3-promotion-20260908/)
|
| 223 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 224 |
## Questions and bugs
|
| 225 |
|
| 226 |
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).
|
|
|
|
| 221 |
|
| 222 |
[Artifact catalog](https://github.com/Oruk-AI/orukeet/blob/main/src/orukeet/artifacts.json) 路 [Native conversion and validation](https://github.com/Oruk-AI/orukeet/tree/main/evidence/r3-promotion-20260908/)
|
| 223 |
|
| 224 |
+
## Hosted API
|
| 225 |
+
|
| 226 |
+
Oruk also serves Orukeet as a hosted English transcription endpoint (preview) at [oruk.ai/models/orukeet](https://oruk.ai/models/orukeet?utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet); it needs an Oruk API key. Limits per the [OpenAPI contract](https://oruk.ai/openapi.json?utm_source=huggingface&utm_medium=model-card&utm_campaign=orukeet): English only; at most 60 seconds of audio per request; 4 MiB for the complete multipart request; no word timestamps (speaker-turn times only when diarization is enabled); usage draws from the plan's separate Orukeet allowance at $0.027 per audio hour. Hosted adds no install or GPU, plus optional emotion scores and speaker diarization on the same request. The local, open-weights path covers 25 languages and runs offline.
|
| 227 |
+
|
| 228 |
## Questions and bugs
|
| 229 |
|
| 230 |
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).
|