funasr1.0

游雁

2024-01-05 32905d8cdedd53dad26680b0bd41397aaf0e51ae

 funasr/models/paraformer/model.py

@@ -22,7 +22,7 @@

from torch.cuda.amp import autocast

from funasr.datasets.audio_datasets.load_audio_extract_fbank import load_audio, extract_fbank
from funasr.utils.load_utils import load_audio_and_text_image_video, extract_fbank, load_audio_and_text_image_video
from funasr.utils import postprocess_utils
from funasr.utils.datadir_writer import DatadirWriter
from funasr.register import tables
@@ -466,7 +466,7 @@
      else:
         # extract fbank feats
         time1 = time.perf_counter()
         audio_sample_list = load_audio(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
         audio_sample_list = load_audio_and_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000), data_type=kwargs.get("data_type", "sound"), tokenizer=tokenizer)
         time2 = time.perf_counter()
         meta_data["load_data"] = f"{time2 - time1:0.3f}"
         speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), frontend=frontend)
@@ -495,6 +495,8 @@

      results = []
      b, n, d = decoder_out.size()
      if isinstance(key[0], (list, tuple)):
         key = key[0]
      for i in range(b):
         x = encoder_out[i, :encoder_out_lens[i], :]
         am_scores = decoder_out[i, :pre_token_length[i], :]
@@ -535,6 +537,7 @@
               text = tokenizer.tokens2text(token)
               
               text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
					
               result_i = {"key": key[i], "text": text_postprocessed}