docs

游雁

2023-09-18 74aa12ee4bbef787236bd382b186a17db40866a6

 funasr/bin/asr_inference_launch.py

@@ -45,7 +45,7 @@
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
from funasr.utils.vad_utils import slice_padding_fbank

from tqdm import tqdm

def inference_asr(
        maxlenratio: float,
@@ -236,6 +236,7 @@
        timestamp_infer_config: Union[Path, str] = None,
        timestamp_model_file: Union[Path, str] = None,
        param_dict: dict = None,
        decoding_ind: int = 0,
        **kwargs,
):
    ncpu = kwargs.get("ncpu", 1)
@@ -290,6 +291,7 @@
        nbest=nbest,
        hotword_list_or_file=hotword_list_or_file,
        clas_scale=clas_scale,
        decoding_ind=decoding_ind,
    )

    speech2text = Speech2TextParaformer(**speech2text_kwargs)
@@ -312,6 +314,7 @@
            **kwargs,
    ):

        decoding_ind = None
        hotword_list_or_file = None
        if param_dict is not None:
            hotword_list_or_file = param_dict.get('hotword')
@@ -319,6 +322,8 @@
            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)
        if param_dict is not None and "decoding_ind" in param_dict:
            decoding_ind = param_dict["decoding_ind"]

        # 3. Build data-iterator
        if data_path_and_name_and_type is None and raw_inputs is not None:
@@ -365,6 +370,7 @@
            # N-best list of (text, token, token_int, hyp_object)

            time_beg = time.time()
            batch["decoding_ind"] = decoding_ind
            results = speech2text(**batch)
            if len(results) < 1:
                hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
@@ -409,7 +415,7 @@
                        ibest_writer["rtf"][key] = rtf_cur

                    if text is not None:
                        if use_timestamp and timestamp is not None:
                        if use_timestamp and timestamp is not None and len(timestamp):
                            postprocessed_result = postprocess_utils.sentence_postprocess(token, timestamp)
                        else:
                            postprocessed_result = postprocess_utils.sentence_postprocess(token)
@@ -421,7 +427,7 @@
                        else:
                            text_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1]
                        item = {'key': key, 'value': text_postprocessed}
                        if timestamp_postprocessed != "":
                        if timestamp_postprocessed != "" or len(timestamp) == 0:
                            item['timestamp'] = timestamp_postprocessed
                        asr_result_list.append(item)
                        finish_count += 1
@@ -645,7 +651,8 @@
            
            batch_size_token_ms_cum = 0
            beg_idx = 0
            for j, _ in enumerate(range(0, n)):
            beg_asr_total = time.time()
            for j, _ in tqdm(enumerate(range(0, n))):
                batch_size_token_ms_cum += (sorted_data[j][0][1] - sorted_data[j][0][0])
                if j < n - 1 and (batch_size_token_ms_cum + sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_ms and (sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_threshold_s:
                    continue
@@ -655,16 +662,17 @@
                beg_idx = end_idx
                batch = {"speech": speech_j, "speech_lengths": speech_lengths_j}
                batch = to_device(batch, device=device)
                print("batch: ", speech_j.shape[0])
                # print("batch: ", speech_j.shape[0])
                beg_asr = time.time()
                results = speech2text(**batch)
                end_asr = time.time()
                print("time cost asr: ", end_asr - beg_asr)
                # print("time cost asr: ", end_asr - beg_asr)

                if len(results) < 1:
                    results = [["", [], [], [], [], [], []]]
                results_sorted.extend(results)

            end_asr_total = time.time()
            print("total time cost asr: ", end_asr_total-beg_asr_total)
            restored_data = [0] * n
            for j in range(n):
                index = sorted_data[j][1]
@@ -686,7 +694,7 @@
            text, token, token_int = result[0], result[1], result[2]
            time_stamp = result[4] if len(result[4]) > 0 else None

            if use_timestamp and time_stamp is not None:
            if use_timestamp and time_stamp is not None and len(time_stamp):
                postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
            else:
                postprocessed_result = postprocess_utils.sentence_postprocess(token)
@@ -711,7 +719,7 @@
            item = {'key': key, 'value': text_postprocessed_punc}
            if text_postprocessed != "":
                item['text_postprocessed'] = text_postprocessed
            if time_stamp_postprocessed != "":
            if time_stamp_postprocessed != "" or len(time_stamp) == 0:
                item['time_stamp'] = time_stamp_postprocessed

            item['sentences'] = time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed)