fix empty timestamp list inference

shixian.shi

2023-09-06 13c2af5de44d2ac4cb09677ab4fb07f37ade2b98

 funasr/bin/asr_inference_launch.py

@@ -409,7 +409,7 @@
                        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 +421,7 @@
                        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
@@ -686,7 +686,7 @@
            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 +711,7 @@
            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)
@@ -1290,6 +1290,7 @@
        quantize_dtype: Optional[str] = "float16",
        streaming: Optional[bool] = False,
        simu_streaming: Optional[bool] = False,
        full_utt: Optional[bool] = False,
        chunk_size: Optional[int] = 16,
        left_context: Optional[int] = 16,
        right_context: Optional[int] = 0,
@@ -1366,6 +1367,7 @@
        quantize_dtype=quantize_dtype,
        streaming=streaming,
        simu_streaming=simu_streaming,
        full_utt=full_utt,
        chunk_size=chunk_size,
        left_context=left_context,
        right_context=right_context,
@@ -1416,7 +1418,7 @@
                        _end = (i + 1) * speech2text._ctx

                        speech2text.streaming_decode(
                            speech[i * speech2text._ctx: _end], is_final=False
                            speech[i * speech2text._ctx: _end + speech2text._right_ctx], is_final=False
                        )

                    final_hyps = speech2text.streaming_decode(
@@ -1424,6 +1426,8 @@
                    )
                elif speech2text.simu_streaming:
                    final_hyps = speech2text.simu_streaming_decode(**batch)
                elif speech2text.full_utt:
                    final_hyps = speech2text.full_utt_decode(**batch)
                else:
                    final_hyps = speech2text(**batch)

@@ -1812,6 +1816,7 @@
    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("--full_utt", type=str2bool, default=False)
    group.add_argument("--chunk_size", type=int, default=16)
    group.add_argument("--left_context", type=int, default=16)
    group.add_argument("--right_context", type=int, default=0)