Merge pull request #956 from alibaba-damo-academy/chenmengzheAAA-patch-4

chenmengzheAAA

2023-09-14 2a66366be4c2715870e4859fd5a5db6e8a9dc00a

 funasr/bin/asr_inference_launch.py

@@ -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=[])
@@ -421,7 +427,7 @@
                        else:
                            text_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1]
                        item = {'key': key, 'value': text_postprocessed}
                        if timestamp_postprocessed != "" or len(timestamp) == 0:
                        if timestamp_postprocessed != "":
                            item['timestamp'] = timestamp_postprocessed
                        asr_result_list.append(item)
                        finish_count += 1
@@ -711,7 +717,7 @@
            item = {'key': key, 'value': text_postprocessed_punc}
            if text_postprocessed != "":
                item['text_postprocessed'] = text_postprocessed
            if time_stamp_postprocessed != "" or len(time_stamp) == 0:
            if time_stamp_postprocessed != "":
                item['time_stamp'] = time_stamp_postprocessed

            item['sentences'] = time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed)
@@ -1289,7 +1295,7 @@
        quantize_modules: Optional[List[str]] = None,
        quantize_dtype: Optional[str] = "float16",
        streaming: Optional[bool] = False,
        simu_streaming: Optional[bool] = False,
        fake_streaming: Optional[bool] = False,
        full_utt: Optional[bool] = False,
        chunk_size: Optional[int] = 16,
        left_context: Optional[int] = 16,
@@ -1366,7 +1372,7 @@
        quantize_modules=quantize_modules,
        quantize_dtype=quantize_dtype,
        streaming=streaming,
        simu_streaming=simu_streaming,
        fake_streaming=fake_streaming,
        full_utt=full_utt,
        chunk_size=chunk_size,
        left_context=left_context,
@@ -1424,8 +1430,8 @@
                    final_hyps = speech2text.streaming_decode(
                        speech[_end: len(speech)], is_final=True
                    )
                elif speech2text.simu_streaming:
                    final_hyps = speech2text.simu_streaming_decode(**batch)
                elif speech2text.fake_streaming:
                    final_hyps = speech2text.fake_streaming_decode(**batch)
                elif speech2text.full_utt:
                    final_hyps = speech2text.full_utt_decode(**batch)
                else:
@@ -1815,7 +1821,7 @@
    group.add_argument("--lm_weight", type=float, default=1.0, help="RNNLM weight")
    group.add_argument("--ngram_weight", type=float, default=0.9, help="ngram weight")
    group.add_argument("--streaming", type=str2bool, default=False)
    group.add_argument("--simu_streaming", type=str2bool, default=False)
    group.add_argument("--fake_streaming", type=str2bool, default=False)
    group.add_argument("--full_utt", type=str2bool, default=False)
    group.add_argument("--chunk_size", type=int, default=16)
    group.add_argument("--left_context", type=int, default=16)