Automatic Speech Recognition
NeMo
ONNX
Safetensors
GGUF
parakeet_tdt
parakeet
tdt
sherpa-onnx
multilingual
speech-recognition
gabor
fastconformer
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
Link the recorded local transcription walkthrough
Browse files
README.md
CHANGED
|
@@ -135,6 +135,8 @@ for a supplied audio file, a reusable runner, actual output and verification
|
|
| 135 |
hashes. The native response contains transcription and window-level segment
|
| 136 |
times; it does not return emotion, speaking-style or speaker-diarization scores.
|
| 137 |
|
|
|
|
|
|
|
| 138 |
[Usage and batch transcription](https://github.com/Oruk-AI/orukeet/blob/main/docs/usage.md)
|
| 139 |
路 [Native runtime and measurements](https://github.com/Oruk-AI/orukeet/blob/main/runtime/README.md)
|
| 140 |
|
|
|
|
| 135 |
hashes. The native response contains transcription and window-level segment
|
| 136 |
times; it does not return emotion, speaking-style or speaker-diarization scores.
|
| 137 |
|
| 138 |
+
[Watch the 39-second recorded example](https://oruk.ai/guides/orukeet-local-transcription#watch) to hear the input and inspect the native Q8 / Metal output. The walkthrough is edited for readability; it is not a speed or accuracy benchmark.
|
| 139 |
+
|
| 140 |
[Usage and batch transcription](https://github.com/Oruk-AI/orukeet/blob/main/docs/usage.md)
|
| 141 |
路 [Native runtime and measurements](https://github.com/Oruk-AI/orukeet/blob/main/runtime/README.md)
|
| 142 |
|