Files
freedakgmail 6116b1f3c6
Update API Documentation / build-api-docs (push) Has been cancelled
Initial commit: FunASR Speech Recognition Toolkit
Add complete FunASR codebase including models, runtime, and documentation.
2026-07-09 22:38:58 +08:00

11 lines
362 B
Python

#!/usr/bin/env python3
"""Detokenize SenseVoice CTC token ids -> text via the SentencePiece bpe model.
Usage: python detok.py <bpe.model> <ids.txt> (ids.txt = space-separated ints)
"""
import sys
import sentencepiece as spm
sp = spm.SentencePieceProcessor(model_file=sys.argv[1])
ids = [int(x) for x in open(sys.argv[2]).read().split()]
print(sp.decode(ids))