Merge pull request #199 from alibaba-damo-academy/dev_xw

zhifu gao

2023-03-16 d783b24ba7d8a03dabfa2139fcbf40c216e0ea3d

 funasr/bin/asr_inference_paraformer.py

@@ -50,7 +50,7 @@

    Examples:
            >>> import soundfile
            >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
            >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
            >>> audio, rate = soundfile.read("speech.wav")
            >>> speech2text(audio)
            [(text, token, token_int, hypothesis object), ...]
@@ -245,7 +245,7 @@
            decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]

        if isinstance(self.asr_model, BiCifParaformer):
            _, _, us_alphas, us_cif_peak = self.asr_model.calc_predictor_timestamp(enc, enc_len,
            _, _, us_alphas, us_peaks = self.asr_model.calc_predictor_timestamp(enc, enc_len,
                                                                                   pre_token_length)  # test no bias cif2

        results = []
@@ -292,7 +292,7 @@

                if isinstance(self.asr_model, BiCifParaformer):
                    _, timestamp = ts_prediction_lfr6_standard(us_alphas[i], 
                                                            us_cif_peak[i], 
                                                            us_peaks[i], 
                                                            copy.copy(token), 
                                                            vad_offset=begin_time)
                    results.append((text, token, token_int, hyp, timestamp, enc_len_batch_total, lfr_factor))