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
@@ -100,10 +101,13 @@
        # logging.info("asr_train_args: {}".format(asr_train_args))
        asr_model.to(dtype=getattr(torch, dtype)).eval()

        ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
        if asr_model.ctc != None:
            ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
            scorers.update(
                ctc=ctc
            )
        token_list = asr_model.token_list
        scorers.update(
            ctc=ctc,
            length_bonus=LengthBonus(len(token_list)),
        )

@@ -171,7 +175,7 @@
        self.converter = converter
        self.tokenizer = tokenizer
        is_use_lm = lm_weight != 0.0 and lm_file is not None
        if ctc_weight == 0.0 and not is_use_lm:
        if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
            beam_search = None
        self.beam_search = beam_search
        logging.info(f"Beam_search: {self.beam_search}")
@@ -231,6 +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]
@@ -598,7 +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]
@@ -632,9 +638,16 @@
                        text_postprocessed, time_stamp_postprocessed, word_lists = postprocessed_result[0], \
                                                                                   postprocessed_result[1], \
                                                                                   postprocessed_result[2]
                        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)
                        if len(word_lists) > 0: 
                            text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
                            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 = []
                            text_postprocessed_punc_time_stamp = ""
                            
                    else:
                        text_postprocessed = ""
                        time_stamp_postprocessed = ""