update asr postprocess_utils

北念

2023-10-10 a4de8b2a0a69ba42c58d6bacb9c9108539a1e280

 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,
@@ -488,6 +488,7 @@
):
    ncpu = kwargs.get("ncpu", 1)
    torch.set_num_threads(ncpu)
    language = kwargs.get("model_lang", None)

    if word_lm_train_config is not None:
        raise NotImplementedError("Word LM is not implemented")
@@ -651,7 +652,8 @@
            
            batch_size_token_ms_cum = 0
            beg_idx = 0
            for j, _ in enumerate(range(0, n)):
            beg_asr_total = time.time()
            for j, _ in enumerate(tqdm(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
@@ -661,16 +663,17 @@
                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]
@@ -692,10 +695,13 @@
            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 and len(time_stamp):
                postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
            if language == "en-bpe":
                postprocessed_result = postprocess_utils.sentence_postprocess_sentencepiece(token)
            else:
                postprocessed_result = postprocess_utils.sentence_postprocess(token)
                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)
            text_postprocessed = ""
            time_stamp_postprocessed = ""
            text_postprocessed_punc = postprocessed_result
@@ -853,7 +859,7 @@
                    "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)), "tail_chunk": False}
        cache["encoder"] = cache_en

        cache_de = {"decode_fsmn": None, "decoder_chunk_look_back": decoder_chunk_look_back, "opt": None}
        cache_de = {"decode_fsmn": None, "decoder_chunk_look_back": decoder_chunk_look_back, "opt": None, "chunk_size": chunk_size}
        cache["decoder"] = cache_de

        return cache
@@ -870,7 +876,7 @@
                        "feats": torch.zeros((batch_size, chunk_size[0] + chunk_size[2], feats_dims)), "tail_chunk": False}
            cache["encoder"] = cache_en

            cache_de = {"decode_fsmn": None, "decoder_chunk_look_back": decoder_chunk_look_back, "opt": None}
            cache_de = {"decode_fsmn": None, "decoder_chunk_look_back": decoder_chunk_look_back, "opt": None, "chunk_size": chunk_size}
            cache["decoder"] = cache_de

        return cache
@@ -982,8 +988,8 @@

        asr_result_list.append(item)
        if is_final:
            cache = _cache_reset(cache, chunk_size=chunk_size, batch_size=1,
                                 encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
            cache = _cache_reset(cache, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, 
                                 decoder_chunk_look_back=decoder_chunk_look_back, batch_size=1)
        return asr_result_list

    return _forward
@@ -1341,7 +1347,7 @@
        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,
@@ -1418,7 +1424,7 @@
        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,
@@ -1476,8 +1482,8 @@
                    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:
@@ -1867,7 +1873,7 @@
    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)