Merge pull request #52 from alibaba-damo-academy/dev

zhifu gao

2023-01-31 2cbebbb33435dc490b6a092f2e5903c7f0e3e33c

 funasr/bin/asr_inference_paraformer_vad_punc.py

@@ -3,6 +3,7 @@
import logging
import sys
import time
import json
from pathlib import Path
from typing import Optional
from typing import Sequence
@@ -234,6 +235,8 @@

        predictor_outs = self.asr_model.calc_predictor(enc, enc_len)
        pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = predictor_outs[0], predictor_outs[1], predictor_outs[2], predictor_outs[3]
        if torch.max(pre_token_length) < 1:
            return []
        pre_token_length = pre_token_length.round().long()
        decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length)
        decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
@@ -601,7 +604,7 @@
                    results = speech2text(**batch)
                    if len(results) < 1:
                        hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
                        results = [[" ", ["<space>"], [2], 0, 1, 6]] * nbest
                        results = [[" ", ["sil"], [2], 0, 1, 6]] * nbest
                    time_end = time.time()
                    forward_time = time_end - time_beg
                    lfr_factor = results[0][-1]
@@ -637,8 +640,9 @@
                                                                                   postprocessed_result[2]
                        if len(word_lists) > 0: 
                            text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
                            text_postprocessed_punc_time_stamp = "predictions: {}  time_stamp: {}".format(
                                text_postprocessed_punc, time_stamp_postprocessed)
                            text_postprocessed_punc_time_stamp = json.dumps({"predictions": text_postprocessed_punc,
                                                                             "time_stamp": time_stamp_postprocessed},
                                                                            ensure_ascii=False)
                        else:
                            text_postprocessed_punc = ""
                            punc_id_list = []