speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

bug fix for empty text

Browse Source
This commit is contained in:
shixian.shi 2024-02-27 10:36:40 +08:00
parent 11815a0726
commit 9844be44e9
3 changed files with 23 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
funasr/auto/auto_frontend.py
View File

@ -1,3 +1,8 @@
#!/usr/bin/env python3
# -*- encoding: utf-8 -*-
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
# MIT License (https://opensource.org/licenses/MIT)
import json
import time
import torch
@ -12,15 +17,14 @@ from omegaconf import DictConfig, OmegaConf, ListConfig
from funasr.register import tables
from funasr.utils.load_utils import load_bytes
from funasr.download.file import download_from_url
from funasr.auto.auto_model import prepare_data_iterator
from funasr.utils.timestamp_tools import timestamp_sentence
from funasr.download.download_from_hub import download_model
from funasr.utils.vad_utils import slice_padding_audio_samples
from funasr.train_utils.set_all_random_seed import set_all_random_seed
from funasr.train_utils.load_pretrained_model import load_pretrained_model
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.utils.timestamp_tools import timestamp_sentence
from funasr.models.campplus.utils import sv_chunk, postprocess, distribute_spk
from funasr.auto.auto_model import prepare_data_iterator
class AutoFrontend:

22
funasr/auto/auto_model.py
View File

@ -1,3 +1,8 @@
#!/usr/bin/env python3
# -*- encoding: utf-8 -*-
# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
# MIT License (https://opensource.org/licenses/MIT)
import json
import time
import copy
@ -12,12 +17,12 @@ from tqdm import tqdm
from funasr.register import tables
from funasr.utils.load_utils import load_bytes
from funasr.download.file import download_from_url
from funasr.utils.timestamp_tools import timestamp_sentence
from funasr.download.download_from_hub import download_model
from funasr.utils.vad_utils import slice_padding_audio_samples
from funasr.utils.load_utils import load_audio_text_image_video
from funasr.train_utils.set_all_random_seed import set_all_random_seed
from funasr.train_utils.load_pretrained_model import load_pretrained_model
from funasr.utils.load_utils import load_audio_text_image_video
from funasr.utils.timestamp_tools import timestamp_sentence
from funasr.models.campplus.utils import sv_chunk, postprocess, distribute_spk
try:
from funasr.models.campplus.cluster_backend import ClusterBackend
@ -381,11 +386,14 @@ class AutoModel:
return_raw_text = kwargs.get('return_raw_text', False)
# step.3 compute punc model
if self.punc_model is not None:
self.punc_kwargs.update(cfg)
punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg)
raw_text = copy.copy(result["text"])
if return_raw_text: result['raw_text'] = raw_text
result["text"] = punc_res[0]["text"]
if not len(result["text"]):
result['raw_text'] = ''
else:
self.punc_kwargs.update(cfg)
punc_res = self.inference(result["text"], model=self.punc_model, kwargs=self.punc_kwargs, **cfg)
raw_text = copy.copy(result["text"])
if return_raw_text: result['raw_text'] = raw_text
result["text"] = punc_res[0]["text"]
else:
raw_text = None

2
funasr/models/seaco_paraformer/model.py
View File

@ -25,8 +25,8 @@ from funasr.models.paraformer.search import Hypothesis
from funasr.train_utils.device_funcs import force_gatherable
from funasr.models.bicif_paraformer.model import BiCifParaformer
from funasr.losses.label_smoothing_loss import LabelSmoothingLoss
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
from funasr.models.transformer.utils.add_sos_eos import add_sos_eos
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
from funasr.models.transformer.utils.nets_utils import make_pad_mask, pad_list
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank