Instructions to use WhissleAI/STT-en-in-tech-misc-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use WhissleAI/STT-en-in-tech-misc-ONNX with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("WhissleAI/STT-en-in-tech-misc-ONNX") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Access Whissle STT English-Indian Tech on Hugging Face
This model is licensed for inference only — no training, fine-tuning, distillation, or reverse engineering permitted. Accept the license to access. Automatic approval.
By clicking "Agree", you accept the Whissle Inference-Only License Agreement. See the LICENSE file for full terms. Key restrictions: INFERENCE ONLY — no training, fine-tuning, distillation, model compression, or reverse engineering permitted. Free for inference use under 100M MAU. "Powered by Whissle" attribution required for redistribution.
Log in or Sign Up to review the conditions and access this model content.
Whissle STT English-Indian Tech
English speech recognition model with Indian accent optimization, designed for technical interviews, coaching sessions, and professional conversations. Features the richest tag classifier in the Whissle STT family — 6 output categories including 26-class behavioral analysis.
Model Details
| Architecture | Conformer-CTC (EncDecCTCModelBPE) + dual-head tag classifier |
| Encoder | 512-dim, Conformer layers |
| Download size | ~484 MB |
| Format | ONNX (CPU and GPU compatible) |
| Sample rate | 16 kHz mono |
| Language | English (Indian accent optimized) |
Tag Classifier Outputs
| Category | Classes | Labels |
|---|---|---|
| Age | 8 | 0-18, 18-30, 30-45, 45-60, 60+, UNCERTAIN, INVALID, NONE |
| Behavior | 26 | EXPLAIN, FACILITATE, FILLER, QUESTION_CLOSED, QUESTION_OPEN, DIRECT, ACKNOWLEDGE, EVALUATE, STRUCTURE, THINK_ALOUD, EXPRESS, INFORM, REASON, ABILITY, COMMIT, QUESTION, ADVISE, REFLECT, AFFIRM, FOLLOW_NEUTRAL, RAISE_CONCERN, REFRAME, SUPPORT, CONFRONT, WARN, NONE |
| Emotion | 7 | NEUTRAL, SAD, HAPPY, ANGRY, FEAR, SURPRISE, NONE |
| Eval | 8 | CORRECT, PROBE, PARTIAL, INCORRECT, HINT, SKIP, NONE, EVAL_NONE |
| Gender | 4 | MALE, FEMALE, OTHER, NONE |
| Role | 3 | INTERVIEWER, INTERVIEWEE, NONE |
Quick Start
git clone https://github.com/WhissleAI/whissle_stt_inference.git
cd whissle_stt_inference
./setup.sh --model en-in-tech-misc
License
Whissle Inference-Only License — inference only, no training/fine-tuning/distillation/reverse engineering. Free under 100M MAU.
- Downloads last month
- 100
Model tree for WhissleAI/STT-en-in-tech-misc-ONNX
Base model
nvidia/parakeet-ctc-0.6b