Merge pull request #207 from alibaba-damo-academy/dev_dzh

zhifu gao

2023-03-10 9be8a443d74d68f179de88fff13b4e8424579d7b

 funasr/bin/asr_inference_paraformer.py

@@ -42,6 +42,7 @@
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
from funasr.export.models.e2e_asr_paraformer import Paraformer as Paraformer_export
from funasr.utils.timestamp_tools import time_stamp_lfr6_pl, time_stamp_sentence


class Speech2Text:
@@ -169,56 +170,8 @@
        self.tokenizer = tokenizer

        # 6. [Optional] Build hotword list from str, local file or url
        # for None 
        if hotword_list_or_file is None:
            self.hotword_list = None
        # for text str input
        elif not os.path.exists(hotword_list_or_file) and not hotword_list_or_file.startswith('http'):
            logging.info("Attempting to parse hotwords as str...")
            self.hotword_list = []
            hotword_str_list = []
            for hw in hotword_list_or_file.strip().split():
                hotword_str_list.append(hw)
                self.hotword_list.append(self.converter.tokens2ids([i for i in hw]))
            self.hotword_list.append([self.asr_model.sos])
            hotword_str_list.append('<s>')
            logging.info("Hotword list: {}.".format(hotword_str_list))
        # for local txt inputs
        elif os.path.exists(hotword_list_or_file):
            logging.info("Attempting to parse hotwords from local txt...")
            self.hotword_list = []
            hotword_str_list = []
            with codecs.open(hotword_list_or_file, 'r') as fin:
                for line in fin.readlines():
                    hw = line.strip()
                    hotword_str_list.append(hw)
                    self.hotword_list.append(self.converter.tokens2ids([i for i in hw]))
                self.hotword_list.append([self.asr_model.sos])
                hotword_str_list.append('<s>')
            logging.info("Initialized hotword list from file: {}, hotword list: {}."
                .format(hotword_list_or_file, hotword_str_list))
        # for url, download and generate txt
        else:
            logging.info("Attempting to parse hotwords from url...")
            work_dir = tempfile.TemporaryDirectory().name
            if not os.path.exists(work_dir):
                os.makedirs(work_dir)
            text_file_path = os.path.join(work_dir, os.path.basename(hotword_list_or_file))
            local_file = requests.get(hotword_list_or_file)
            open(text_file_path, "wb").write(local_file.content)
            hotword_list_or_file = text_file_path
            self.hotword_list = []
            hotword_str_list = []
            with codecs.open(hotword_list_or_file, 'r') as fin:
                for line in fin.readlines():
                    hw = line.strip()
                    hotword_str_list.append(hw)
                    self.hotword_list.append(self.converter.tokens2ids([i for i in hw]))
                self.hotword_list.append([self.asr_model.sos])
                hotword_str_list.append('<s>')
            logging.info("Initialized hotword list from file: {}, hotword list: {}."
                .format(hotword_list_or_file, hotword_str_list))

        self.hotword_list = None
        self.hotword_list = self.generate_hotwords_list(hotword_list_or_file)

        is_use_lm = lm_weight != 0.0 and lm_file is not None
        if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
@@ -238,7 +191,8 @@

    @torch.no_grad()
    def __call__(
            self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None
            self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None,
            begin_time: int = 0, end_time: int = None,
    ):
        """Inference

@@ -290,6 +244,10 @@
            decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length, hw_list=self.hotword_list)
            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,
                                                                                   pre_token_length)  # test no bias cif2

        results = []
        b, n, d = decoder_out.size()
        for i in range(b):
@@ -332,10 +290,68 @@
                else:
                    text = None

                results.append((text, token, token_int, hyp, enc_len_batch_total, lfr_factor))
                if isinstance(self.asr_model, BiCifParaformer):
                    timestamp = time_stamp_lfr6_pl(us_alphas[i], us_cif_peak[i], copy.copy(token), begin_time, end_time)
                    results.append((text, token, token_int, hyp, timestamp, enc_len_batch_total, lfr_factor))
                else:
                    results.append((text, token, token_int, hyp, enc_len_batch_total, lfr_factor))

        # assert check_return_type(results)
        return results

    def generate_hotwords_list(self, hotword_list_or_file):
        # for None
        if hotword_list_or_file is None:
            hotword_list = None
        # for local txt inputs
        elif os.path.exists(hotword_list_or_file) and hotword_list_or_file.endswith('.txt'):
            logging.info("Attempting to parse hotwords from local txt...")
            hotword_list = []
            hotword_str_list = []
            with codecs.open(hotword_list_or_file, 'r') as fin:
                for line in fin.readlines():
                    hw = line.strip()
                    hotword_str_list.append(hw)
                    hotword_list.append(self.converter.tokens2ids([i for i in hw]))
                hotword_list.append([self.asr_model.sos])
                hotword_str_list.append('<s>')
            logging.info("Initialized hotword list from file: {}, hotword list: {}."
                         .format(hotword_list_or_file, hotword_str_list))
        # for url, download and generate txt
        elif hotword_list_or_file.startswith('http'):
            logging.info("Attempting to parse hotwords from url...")
            work_dir = tempfile.TemporaryDirectory().name
            if not os.path.exists(work_dir):
                os.makedirs(work_dir)
            text_file_path = os.path.join(work_dir, os.path.basename(hotword_list_or_file))
            local_file = requests.get(hotword_list_or_file)
            open(text_file_path, "wb").write(local_file.content)
            hotword_list_or_file = text_file_path
            hotword_list = []
            hotword_str_list = []
            with codecs.open(hotword_list_or_file, 'r') as fin:
                for line in fin.readlines():
                    hw = line.strip()
                    hotword_str_list.append(hw)
                    hotword_list.append(self.converter.tokens2ids([i for i in hw]))
                hotword_list.append([self.asr_model.sos])
                hotword_str_list.append('<s>')
            logging.info("Initialized hotword list from file: {}, hotword list: {}."
                         .format(hotword_list_or_file, hotword_str_list))
        # for text str input
        elif not hotword_list_or_file.endswith('.txt'):
            logging.info("Attempting to parse hotwords as str...")
            hotword_list = []
            hotword_str_list = []
            for hw in hotword_list_or_file.strip().split():
                hotword_str_list.append(hw)
                hotword_list.append(self.converter.tokens2ids([i for i in hw]))
            hotword_list.append([self.asr_model.sos])
            hotword_str_list.append('<s>')
            logging.info("Hotword list: {}.".format(hotword_str_list))
        else:
            hotword_list = None
        return hotword_list

class Speech2TextExport:
    """Speech2TextExport class
@@ -648,7 +664,17 @@
            output_dir_v2: Optional[str] = None,
            fs: dict = None,
            param_dict: dict = None,
            **kwargs,
    ):

        hotword_list_or_file = None
        if param_dict is not None:
            hotword_list_or_file = param_dict.get('hotword')
        if 'hotword' in kwargs:
            hotword_list_or_file = kwargs['hotword']
        if hotword_list_or_file is not None or 'hotword' in kwargs:
            speech2text.hotword_list = speech2text.generate_hotwords_list(hotword_list_or_file)

        # 3. Build data-iterator
        if data_path_and_name_and_type is None and raw_inputs is not None:
            if isinstance(raw_inputs, torch.Tensor):
@@ -666,6 +692,11 @@
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )

        if param_dict is not None:
            use_timestamp = param_dict.get('use_timestamp', True)
        else:
            use_timestamp = True

        forward_time_total = 0.0
        length_total = 0.0
@@ -708,7 +739,9 @@
                result = [results[batch_id][:-2]]

                key = keys[batch_id]
                for n, (text, token, token_int, hyp) in zip(range(1, nbest + 1), result):
                for n, result in zip(range(1, nbest + 1), result):
                    text, token, token_int, hyp = result[0], result[1], result[2], result[3]
                    time_stamp = None if len(result) < 5 else result[4]
                    # Create a directory: outdir/{n}best_recog
                    if writer is not None:
                        ibest_writer = writer[f"{n}best_recog"]
@@ -720,8 +753,20 @@
                        ibest_writer["rtf"][key] = rtf_cur

                    if text is not None:
                        text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
                        if use_timestamp and time_stamp is not None:
                            postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
                        else:
                            postprocessed_result = postprocess_utils.sentence_postprocess(token)
                        time_stamp_postprocessed = ""
                        if len(postprocessed_result) == 3:
                            text_postprocessed, time_stamp_postprocessed, word_lists = postprocessed_result[0], \
                                                                                       postprocessed_result[1], \
                                                                                       postprocessed_result[2]
                        else:
                            text_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1]
                        item = {'key': key, 'value': text_postprocessed}
                        if time_stamp_postprocessed != "":
                            item['time_stamp'] = time_stamp_postprocessed
                        asr_result_list.append(item)
                        finish_count += 1
                        # asr_utils.print_progress(finish_count / file_count)