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