From d80ac2fd2df4e7fb8a28acfa512bb11472b5cc99 Mon Sep 17 00:00:00 2001
From: liugz18 <57401541+liugz18@users.noreply.github.com>
Date: 星期四, 18 七月 2024 21:34:55 +0800
Subject: [PATCH] Rename 'res' in line 514 to avoid with naming conflict with line 365

---
 funasr/models/campplus/utils.py |  172 ++++++++++++++++++++++----------------------------------
 1 files changed, 68 insertions(+), 104 deletions(-)

diff --git a/funasr/models/campplus/utils.py b/funasr/models/campplus/utils.py
index 399be4b..4addd0a 100644
--- a/funasr/models/campplus/utils.py
+++ b/funasr/models/campplus/utils.py
@@ -25,15 +25,13 @@
     audio_dur = 0
     for i in range(len(audio)):
         seg = audio[i]
-        assert seg[1] >= seg[0], 'modelscope error: Wrong time stamps.'
-        assert isinstance(seg[2], np.ndarray), 'modelscope error: Wrong data type.'
-        assert int(seg[1] * 16000) - int(
-            seg[0] * 16000
-        ) == seg[2].shape[
-            0], 'modelscope error: audio data in list is inconsistent with time length.'
+        assert seg[1] >= seg[0], "modelscope error: Wrong time stamps."
+        assert isinstance(seg[2], np.ndarray), "modelscope error: Wrong data type."
+        assert (
+            int(seg[1] * 16000) - int(seg[0] * 16000) == seg[2].shape[0]
+        ), "modelscope error: audio data in list is inconsistent with time length."
         if i > 0:
-            assert seg[0] >= audio[
-                i - 1][1], 'modelscope error: Wrong time stamps.'
+            assert seg[0] >= audio[i - 1][1], "modelscope error: Wrong time stamps."
         audio_dur += seg[1] - seg[0]
     return audio_dur
     # assert audio_dur > 5, 'modelscope error: The effective audio duration is too short.'
@@ -44,39 +42,38 @@
     for i in range(len(inputs)):
         if isinstance(inputs[i], str):
             file_bytes = File.read(inputs[i])
-            data, fs = sf.load(io.BytesIO(file_bytes), dtype='float32')
+            data, fs = sf.load(io.BytesIO(file_bytes), dtype="float32")
             if len(data.shape) == 2:
                 data = data[:, 0]
             data = torch.from_numpy(data).unsqueeze(0)
             data = data.squeeze(0)
         elif isinstance(inputs[i], np.ndarray):
-            assert len(
-                inputs[i].shape
-            ) == 1, 'modelscope error: Input array should be [N, T]'
+            assert len(inputs[i].shape) == 1, "modelscope error: Input array should be [N, T]"
             data = inputs[i]
-            if data.dtype in ['int16', 'int32', 'int64']:
-                data = (data / (1 << 15)).astype('float32')
+            if data.dtype in ["int16", "int32", "int64"]:
+                data = (data / (1 << 15)).astype("float32")
             else:
-                data = data.astype('float32')
+                data = data.astype("float32")
             data = torch.from_numpy(data)
         else:
             raise ValueError(
-                'modelscope error: The input type is restricted to audio address and nump array.'
+                "modelscope error: The input type is restricted to audio address and nump array."
             )
         output.append(data)
     return output
 
 
-def sv_chunk(vad_segments: list, fs = 16000) -> list:
+def sv_chunk(vad_segments: list, fs=16000) -> list:
     config = {
-            'seg_dur': 1.5,
-            'seg_shift': 0.75,
-        }
+        "seg_dur": 1.5,
+        "seg_shift": 0.75,
+    }
+
     def seg_chunk(seg_data):
         seg_st = seg_data[0]
         data = seg_data[2]
-        chunk_len = int(config['seg_dur'] * fs)
-        chunk_shift = int(config['seg_shift'] * fs)
+        chunk_len = int(config["seg_dur"] * fs)
+        chunk_shift = int(config["seg_shift"] * fs)
         last_chunk_ed = 0
         seg_res = []
         for chunk_st in range(0, data.shape[0], chunk_shift):
@@ -87,13 +84,8 @@
             chunk_st = max(0, chunk_ed - chunk_len)
             chunk_data = data[chunk_st:chunk_ed]
             if chunk_data.shape[0] < chunk_len:
-                chunk_data = np.pad(chunk_data,
-                                    (0, chunk_len - chunk_data.shape[0]),
-                                    'constant')
-            seg_res.append([
-                chunk_st / fs + seg_st, chunk_ed / fs + seg_st,
-                chunk_data
-            ])
+                chunk_data = np.pad(chunk_data, (0, chunk_len - chunk_data.shape[0]), "constant")
+            seg_res.append([chunk_st / fs + seg_st, chunk_ed / fs + seg_st, chunk_data])
         return seg_res
 
     segs = []
@@ -108,8 +100,7 @@
     feature_times = []
     feature_lengths = []
     for au in audio:
-        feature = Kaldi.fbank(
-            au.unsqueeze(0), num_mel_bins=80)
+        feature = Kaldi.fbank(au.unsqueeze(0), num_mel_bins=80)
         feature = feature - feature.mean(dim=0, keepdim=True)
         features.append(feature)
         feature_times.append(au.shape[0])
@@ -120,8 +111,9 @@
     return features_padded, feature_lengths, feature_times
 
 
-def postprocess(segments: list, vad_segments: list,
-                labels: np.ndarray, embeddings: np.ndarray) -> list:
+def postprocess(
+    segments: list, vad_segments: list, labels: np.ndarray, embeddings: np.ndarray
+) -> list:
     assert len(segments) == len(labels)
     labels = correct_labels(labels)
     distribute_res = []
@@ -166,17 +158,18 @@
         new_labels.append(id2id[i])
     return np.array(new_labels)
 
+
 def merge_seque(distribute_res):
     res = [distribute_res[0]]
     for i in range(1, len(distribute_res)):
-        if distribute_res[i][2] != res[-1][2] or distribute_res[i][
-                0] > res[-1][1]:
+        if distribute_res[i][2] != res[-1][2] or distribute_res[i][0] > res[-1][1]:
             res.append(distribute_res[i])
         else:
             res[-1][1] = distribute_res[i][1]
     return res
 
-def smooth(res, mindur=1):
+
+def smooth(res, mindur=0.7):
     # if only one segment, return directly
     if len(res) < 2:
         return res
@@ -200,24 +193,21 @@
 
 
 def distribute_spk(sentence_list, sd_time_list):
-    sd_sentence_list = []
+    sd_time_list = [(spk_st * 1000, spk_ed * 1000, spk) for spk_st, spk_ed, spk in sd_time_list]
     for d in sentence_list:
         sentence_start = d['start']
         sentence_end = d['end']
         sentence_spk = 0
         max_overlap = 0
-        for sd_time in sd_time_list:
-            spk_st, spk_ed, spk = sd_time
-            spk_st = spk_st*1000
-            spk_ed = spk_ed*1000
-            overlap = max(
-                min(sentence_end, spk_ed) - max(sentence_start, spk_st), 0)
+        for spk_st, spk_ed, spk in sd_time_list:
+            overlap = max(min(sentence_end, spk_ed) - max(sentence_start, spk_st), 0)
             if overlap > max_overlap:
                 max_overlap = overlap
                 sentence_spk = spk
+            if overlap > 0 and sentence_spk == spk:
+                max_overlap += overlap
         d['spk'] = int(sentence_spk)
-        sd_sentence_list.append(d)
-    return sd_sentence_list
+    return sentence_list
 
 
 class Storage(metaclass=ABCMeta):
@@ -241,10 +231,7 @@
         pass
 
     @abstractmethod
-    def write_text(self,
-                   obj: str,
-                   filepath: Union[str, Path],
-                   encoding: str = 'utf-8') -> None:
+    def write_text(self, obj: str, filepath: Union[str, Path], encoding: str = "utf-8") -> None:
         pass
 
 
@@ -260,13 +247,11 @@
         Returns:
             bytes: Expected bytes object.
         """
-        with open(filepath, 'rb') as f:
+        with open(filepath, "rb") as f:
             content = f.read()
         return content
 
-    def read_text(self,
-                  filepath: Union[str, Path],
-                  encoding: str = 'utf-8') -> str:
+    def read_text(self, filepath: Union[str, Path], encoding: str = "utf-8") -> str:
         """Read data from a given ``filepath`` with 'r' mode.
 
         Args:
@@ -277,7 +262,7 @@
         Returns:
             str: Expected text reading from ``filepath``.
         """
-        with open(filepath, 'r', encoding=encoding) as f:
+        with open(filepath, "r", encoding=encoding) as f:
             value_buf = f.read()
         return value_buf
 
@@ -296,13 +281,10 @@
         if dirname and not os.path.exists(dirname):
             os.makedirs(dirname, exist_ok=True)
 
-        with open(filepath, 'wb') as f:
+        with open(filepath, "wb") as f:
             f.write(obj)
 
-    def write_text(self,
-                   obj: str,
-                   filepath: Union[str, Path],
-                   encoding: str = 'utf-8') -> None:
+    def write_text(self, obj: str, filepath: Union[str, Path], encoding: str = "utf-8") -> None:
         """Write data to a given ``filepath`` with 'w' mode.
 
         Note:
@@ -319,14 +301,11 @@
         if dirname and not os.path.exists(dirname):
             os.makedirs(dirname, exist_ok=True)
 
-        with open(filepath, 'w', encoding=encoding) as f:
+        with open(filepath, "w", encoding=encoding) as f:
             f.write(obj)
 
     @contextlib.contextmanager
-    def as_local_path(
-            self,
-            filepath: Union[str,
-                            Path]) -> Generator[Union[str, Path], None, None]:
+    def as_local_path(self, filepath: Union[str, Path]) -> Generator[Union[str, Path], None, None]:
         """Only for unified API and do nothing."""
         yield filepath
 
@@ -346,8 +325,7 @@
         return r.text
 
     @contextlib.contextmanager
-    def as_local_path(
-            self, filepath: str) -> Generator[Union[str, Path], None, None]:
+    def as_local_path(self, filepath: str) -> Generator[Union[str, Path], None, None]:
         """Download a file from ``filepath``.
 
         ``as_local_path`` is decorated by :meth:`contextlib.contextmanager`. It
@@ -373,14 +351,10 @@
             os.remove(f.name)
 
     def write(self, obj: bytes, url: Union[str, Path]) -> None:
-        raise NotImplementedError('write is not supported by HTTP Storage')
+        raise NotImplementedError("write is not supported by HTTP Storage")
 
-    def write_text(self,
-                   obj: str,
-                   url: Union[str, Path],
-                   encoding: str = 'utf-8') -> None:
-        raise NotImplementedError(
-            'write_text is not supported by HTTP Storage')
+    def write_text(self, obj: str, url: Union[str, Path], encoding: str = "utf-8") -> None:
+        raise NotImplementedError("write_text is not supported by HTTP Storage")
 
 
 class OSSStorage(Storage):
@@ -388,20 +362,16 @@
 
     def __init__(self, oss_config_file=None):
         # read from config file or env var
-        raise NotImplementedError(
-            'OSSStorage.__init__ to be implemented in the future')
+        raise NotImplementedError("OSSStorage.__init__ to be implemented in the future")
 
     def read(self, filepath):
-        raise NotImplementedError(
-            'OSSStorage.read to be implemented in the future')
+        raise NotImplementedError("OSSStorage.read to be implemented in the future")
 
-    def read_text(self, filepath, encoding='utf-8'):
-        raise NotImplementedError(
-            'OSSStorage.read_text to be implemented in the future')
+    def read_text(self, filepath, encoding="utf-8"):
+        raise NotImplementedError("OSSStorage.read_text to be implemented in the future")
 
     @contextlib.contextmanager
-    def as_local_path(
-            self, filepath: str) -> Generator[Union[str, Path], None, None]:
+    def as_local_path(self, filepath: str) -> Generator[Union[str, Path], None, None]:
         """Download a file from ``filepath``.
 
         ``as_local_path`` is decorated by :meth:`contextlib.contextmanager`. It
@@ -427,15 +397,10 @@
             os.remove(f.name)
 
     def write(self, obj: bytes, filepath: Union[str, Path]) -> None:
-        raise NotImplementedError(
-            'OSSStorage.write to be implemented in the future')
+        raise NotImplementedError("OSSStorage.write to be implemented in the future")
 
-    def write_text(self,
-                   obj: str,
-                   filepath: Union[str, Path],
-                   encoding: str = 'utf-8') -> None:
-        raise NotImplementedError(
-            'OSSStorage.write_text to be implemented in the future')
+    def write_text(self, obj: str, filepath: Union[str, Path], encoding: str = "utf-8") -> None:
+        raise NotImplementedError("OSSStorage.write_text to be implemented in the future")
 
 
 G_STORAGES = {}
@@ -443,27 +408,26 @@
 
 class File(object):
     _prefix_to_storage: dict = {
-        'oss': OSSStorage,
-        'http': HTTPStorage,
-        'https': HTTPStorage,
-        'local': LocalStorage,
+        "oss": OSSStorage,
+        "http": HTTPStorage,
+        "https": HTTPStorage,
+        "local": LocalStorage,
     }
 
     @staticmethod
     def _get_storage(uri):
-        assert isinstance(uri,
-                          str), f'uri should be str type, but got {type(uri)}'
+        assert isinstance(uri, str), f"uri should be str type, but got {type(uri)}"
 
-        if '://' not in uri:
+        if "://" not in uri:
             # local path
-            storage_type = 'local'
+            storage_type = "local"
         else:
-            prefix, _ = uri.split('://')
+            prefix, _ = uri.split("://")
             storage_type = prefix
 
-        assert storage_type in File._prefix_to_storage, \
-            f'Unsupported uri {uri}, valid prefixs: '\
-            f'{list(File._prefix_to_storage.keys())}'
+        assert storage_type in File._prefix_to_storage, (
+            f"Unsupported uri {uri}, valid prefixs: " f"{list(File._prefix_to_storage.keys())}"
+        )
 
         if storage_type not in G_STORAGES:
             G_STORAGES[storage_type] = File._prefix_to_storage[storage_type]()
@@ -484,7 +448,7 @@
         return storage.read(uri)
 
     @staticmethod
-    def read_text(uri: Union[str, Path], encoding: str = 'utf-8') -> str:
+    def read_text(uri: Union[str, Path], encoding: str = "utf-8") -> str:
         """Read data from a given ``filepath`` with 'r' mode.
 
         Args:
@@ -514,7 +478,7 @@
         return storage.write(obj, uri)
 
     @staticmethod
-    def write_text(obj: str, uri: str, encoding: str = 'utf-8') -> None:
+    def write_text(obj: str, uri: str, encoding: str = "utf-8") -> None:
         """Write data to a given ``filepath`` with 'w' mode.
 
         Note:

--
Gitblit v1.9.1