File size: 2,014 Bytes
c4c24a9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | """Classify voice-note transcripts with Voice-Note-Intent-Classifier v0.1.
pip install sentence-transformers numpy
python predict.py "um add milk eggs and the oat milk to the list"
Or from Python:
from predict import IntentClassifier
clf = IntentClassifier(".") # folder containing head.json
clf.predict(["dentist thursday at four thirty"])
Output per transcript follows the router contract: scores for every label, the
labels above their thresholds, and `abstain` when none clears its threshold.
"""
import json
import sys
from pathlib import Path
import numpy as np
from sentence_transformers import SentenceTransformer
class IntentClassifier:
def __init__(self, path="."):
cfg = json.loads((Path(path) / "head.json").read_text())
self.cfg = cfg
self.labels = cfg["labels"]
self.coef = np.array(cfg["coef"])
self.intercept = np.array(cfg["intercept"])
self.thresholds = np.array([cfg["thresholds"][l] for l in self.labels])
self.encoder = SentenceTransformer(cfg["encoder"], device="cpu")
self.encoder.max_seq_length = cfg["max_seq_length"]
def predict(self, transcripts):
emb = self.encoder.encode(list(transcripts), normalize_embeddings=self.cfg["normalize_embeddings"])
probs = 1 / (1 + np.exp(-(emb @ self.coef.T + self.intercept)))
out = []
for p in probs:
labels = [l for l, s, t in zip(self.labels, p, self.thresholds) if s >= t]
out.append({
"model_version": self.cfg["model_version"],
"taxonomy_version": self.cfg["taxonomy_version"],
"scores": {l: round(float(s), 4) for l, s in zip(self.labels, p)},
"labels": labels,
"abstain": not labels,
})
return out
if __name__ == "__main__":
clf = IntentClassifier(Path(__file__).parent)
print(json.dumps(clf.predict(sys.argv[1:] or ["need to get milk eggs and dish soap"]), indent=2))
|