Text Classification
Transformers
ONNX
Safetensors
bert
barge-in
backchannel
multilingual
experimental
text-embeddings-inference
Instructions to use HashNuke/barge-in-detector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HashNuke/barge-in-detector with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="HashNuke/barge-in-detector")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("HashNuke/barge-in-detector") model = AutoModelForSequenceClassification.from_pretrained("HashNuke/barge-in-detector", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download onnx/metadata.json from HashNuke/barge-in-detector: direct link, hf CLI and curl.
- Browser
- Download file 796 Bytes
-
https://huggingface.co/HashNuke/barge-in-detector/resolve/main/onnx/metadata.json
- Command line
-
hf download hf://HashNuke/barge-in-detector/onnx/metadata.json
-
curl -L -o metadata.json https://huggingface.co/HashNuke/barge-in-detector/resolve/main/onnx/metadata.json
796 Bytes
| { | |
| "schema_version": 1, | |
| "labels": [ | |
| "backchannel", | |
| "barge_in" | |
| ], | |
| "max_length": 64, | |
| "pad_id": 1, | |
| "pad_token": "<pad>", | |
| "model_file": "model_int8.onnx", | |
| "calibrated": false, | |
| "threshold": 0.5, | |
| "quantization": "Dynamic signed int8, per-channel; MatMul/Gemm/Attention. Embeddings remain fp32.", | |
| "fused_operator_counts": { | |
| "EmbedLayerNormalization": 1, | |
| "Attention": 12, | |
| "MultiHeadAttention": 0, | |
| "Gelu": 0, | |
| "FastGelu": 0, | |
| "BiasGelu": 12, | |
| "GemmFastGelu": 0, | |
| "LayerNormalization": 0, | |
| "SimplifiedLayerNormalization": 0, | |
| "SkipLayerNormalization": 24, | |
| "SkipSimplifiedLayerNormalization": 0, | |
| "RotaryEmbedding": 0, | |
| "QOrderedAttention": 0, | |
| "QOrderedGelu": 0, | |
| "QOrderedLayerNormalization": 0, | |
| "QOrderedMatMul": 0 | |
| } | |
| } | |