freedakgmail
6116b1f3c6
Update API Documentation / build-api-docs (push) Has been cancelled
Add complete FunASR codebase including models, runtime, and documentation.
9 lines
409 B
Python
9 lines
409 B
Python
#!/usr/bin/env python3
|
|
"""Detokenize Paraformer token ids -> text via tokens.json.
|
|
Usage: python detok_paraformer.py <tokens.json> <ids.txt>"""
|
|
import sys, json
|
|
toks = json.load(open(sys.argv[1]))
|
|
ids = [int(x) for x in open(sys.argv[2]).read().split() if int(x) not in (1, 2)] # drop sos/eos
|
|
out = "".join(toks[i] for i in ids if 0 <= i < len(toks))
|
|
print(out.replace("@@", "").replace("▁", " ").strip())
|