Access Whissle STT SLURP Intent on Hugging Face
This model is licensed for inference only — no training, fine-tuning, distillation, or reverse engineering permitted. Accept the license and provide your contact information to access. Requests are processed automatically.
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 SLURP Intent
English ASR with SLURP intent classification. Single-head model trained on the SLURP dataset for intent detection in spoken language understanding.
- Parameters: 600M
- Architecture: Single-head (nvidia/parakeet-ctc-0.6b)
- Languages: English
- Format: ONNX (CPU-optimized)
Quick Start
Use with the Whissle STT Inference Server:
git clone https://github.com/WhissleAI/whissle_stt_inference.git
cd whissle_stt_inference
./setup.sh --model slurp
Or load directly with ONNX Runtime:
import onnxruntime as ort
session = ort.InferenceSession("model.onnx", providers=["CPUExecutionProvider"])
# Prepare mel-spectrogram input and run inference
outputs = session.run(None, {"audio_signal": mel_features, "length": lengths})
License
Licensed under the Whissle Inference-Only License. Inference only — no training, fine-tuning, distillation, or reverse engineering. Free for inference use under 100M MAU.
- Downloads last month
- 6
Model tree for WhissleAI/STT-slurp-intent-ONNX
Base model
nvidia/parakeet-ctc-0.6b