From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/bin/diar_infer.py | 67 ---------------------------------
1 files changed, 1 insertions(+), 66 deletions(-)
diff --git a/funasr/bin/diar_infer.py b/funasr/bin/diar_infer.py
index 7c41b60..6fc1da1 100755
--- a/funasr/bin/diar_infer.py
+++ b/funasr/bin/diar_infer.py
@@ -15,7 +15,6 @@
import torch
from scipy.ndimage import median_filter
from torch.nn import functional as F
-from typeguard import check_argument_types
from funasr.models.frontend.wav_frontend import WavFrontendMel23
from funasr.tasks.diar import DiarTask
@@ -45,7 +44,6 @@
device: str = "cpu",
dtype: str = "float32",
):
- assert check_argument_types()
# 1. Build Diarization model
diar_model, diar_train_args = build_model_from_file(
@@ -88,7 +86,6 @@
diarization results
"""
- assert check_argument_types()
# Input as audio signal
if isinstance(speech, np.ndarray):
speech = torch.tensor(speech)
@@ -106,36 +103,6 @@
results = self.diar_model.estimate_sequential(**batch)
return results
-
- @staticmethod
- def from_pretrained(
- model_tag: Optional[str] = None,
- **kwargs: Optional[Any],
- ):
- """Build Speech2Diarization instance from the pretrained model.
-
- Args:
- model_tag (Optional[str]): Model tag of the pretrained models.
- Currently, the tags of espnet_model_zoo are supported.
-
- Returns:
- Speech2Diarization: Speech2Diarization instance.
-
- """
- if model_tag is not None:
- try:
- from espnet_model_zoo.downloader import ModelDownloader
-
- except ImportError:
- logging.error(
- "`espnet_model_zoo` is not installed. "
- "Please install via `pip install -U espnet_model_zoo`."
- )
- raise
- d = ModelDownloader()
- kwargs.update(**d.download_and_unpack(model_tag))
-
- return Speech2DiarizationEEND(**kwargs)
class Speech2DiarizationSOND:
@@ -163,7 +130,6 @@
smooth_size: int = 83,
dur_threshold: float = 10,
):
- assert check_argument_types()
# TODO: 1. Build Diarization model
diar_model, diar_train_args = build_model_from_file(
@@ -213,7 +179,7 @@
@staticmethod
def seq2arr(seq, vec_dim=8):
- def int2vec(x, vec_dim=8, dtype=np.int):
+ def int2vec(x, vec_dim=8, dtype=np.int32):
b = ('{:0' + str(vec_dim) + 'b}').format(x)
# little-endian order: lower bit first
return (np.array(list(b)[::-1]) == '1').astype(dtype)
@@ -283,7 +249,6 @@
diarization results for each speaker
"""
- assert check_argument_types()
# Input as audio signal
if isinstance(speech, np.ndarray):
speech = torch.tensor(speech)
@@ -305,33 +270,3 @@
results, pse_labels = self.post_processing(logits, profile.shape[1], output_format)
return results, pse_labels
-
- @staticmethod
- def from_pretrained(
- model_tag: Optional[str] = None,
- **kwargs: Optional[Any],
- ):
- """Build Speech2Xvector instance from the pretrained model.
-
- Args:
- model_tag (Optional[str]): Model tag of the pretrained models.
- Currently, the tags of espnet_model_zoo are supported.
-
- Returns:
- Speech2Xvector: Speech2Xvector instance.
-
- """
- if model_tag is not None:
- try:
- from espnet_model_zoo.downloader import ModelDownloader
-
- except ImportError:
- logging.error(
- "`espnet_model_zoo` is not installed. "
- "Please install via `pip install -U espnet_model_zoo`."
- )
- raise
- d = ModelDownloader()
- kwargs.update(**d.download_and_unpack(model_tag))
-
- return Speech2DiarizationSOND(**kwargs)
--
Gitblit v1.9.1