| | |
|---|
| | | import logging |
|---|
| | | import sys |
|---|
| | | import time |
|---|
| | | import json |
|---|
| | | from pathlib import Path |
|---|
| | | from typing import Optional |
|---|
| | | from typing import Sequence |
|---|
| | |
|---|
| | | 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}") |
|---|
| | |
|---|
| | | |
|---|
| | | 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] |
|---|
| | |
|---|
| | | 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] |
|---|
| | |
|---|
| | | 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 = "" |
|---|
| | |
|---|
| | | time_stamp_postprocessed)) |
|---|
| | | |
|---|
| | | logging.info("decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}". |
|---|
| | | format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor))) |
|---|
| | | format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor+1e-6))) |
|---|
| | | return asr_result_list |
|---|
| | | return _forward |
|---|
| | | |
|---|
