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 | 124 ++++++++---------------------------------
1 files changed, 25 insertions(+), 99 deletions(-)
diff --git a/funasr/bin/diar_infer.py b/funasr/bin/diar_infer.py
index f698a66..6fc1da1 100755
--- a/funasr/bin/diar_infer.py
+++ b/funasr/bin/diar_infer.py
@@ -1,40 +1,27 @@
#!/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 argparse
import logging
import os
-import sys
+from collections import OrderedDict
from pathlib import Path
from typing import Any
-from typing import List
from typing import Optional
-from typing import Sequence
-from typing import Tuple
from typing import Union
-from collections import OrderedDict
import numpy as np
-import soundfile
import torch
-from torch.nn import functional as F
-from typeguard import check_argument_types
-from typeguard import check_return_type
-
-from funasr.utils.cli_utils import get_commandline_args
-from funasr.tasks.diar import DiarTask
-from funasr.tasks.diar import EENDOLADiarTask
-from funasr.torch_utils.device_funcs import to_device
-from funasr.torch_utils.set_all_random_seed import set_all_random_seed
-from funasr.utils import config_argparse
-from funasr.utils.types import str2bool
-from funasr.utils.types import str2triple_str
-from funasr.utils.types import str_or_none
from scipy.ndimage import median_filter
-from funasr.utils.misc import statistic_model_parameters
-from funasr.datasets.iterable_dataset import load_bytes
+from torch.nn import functional as F
+
from funasr.models.frontend.wav_frontend import WavFrontendMel23
+from funasr.tasks.diar import DiarTask
+from funasr.build_utils.build_model_from_file import build_model_from_file
+from funasr.torch_utils.device_funcs import to_device
+from funasr.utils.misc import statistic_model_parameters
+
class Speech2DiarizationEEND:
"""Speech2Diarlization class
@@ -57,13 +44,14 @@
device: str = "cpu",
dtype: str = "float32",
):
- assert check_argument_types()
# 1. Build Diarization model
- diar_model, diar_train_args = EENDOLADiarTask.build_model_from_file(
+ diar_model, diar_train_args = build_model_from_file(
config_file=diar_train_config,
model_file=diar_model_file,
- device=device
+ device=device,
+ task_name="diar",
+ mode="eend-ola",
)
frontend = None
if diar_train_args.frontend is not None and diar_train_args.frontend_conf is not None:
@@ -98,7 +86,6 @@
diarization results
"""
- assert check_argument_types()
# Input as audio signal
if isinstance(speech, np.ndarray):
speech = torch.tensor(speech)
@@ -116,36 +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:
@@ -173,13 +130,14 @@
smooth_size: int = 83,
dur_threshold: float = 10,
):
- assert check_argument_types()
# TODO: 1. Build Diarization model
- diar_model, diar_train_args = DiarTask.build_model_from_file(
+ diar_model, diar_train_args = build_model_from_file(
config_file=diar_train_config,
model_file=diar_model_file,
- device=device
+ device=device,
+ task_name="diar",
+ mode="sond",
)
logging.info("diar_model: {}".format(diar_model))
logging.info("model parameter number: {}".format(statistic_model_parameters(diar_model)))
@@ -221,7 +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)
@@ -234,8 +192,11 @@
new_seq.append(x)
else:
idx_list = np.where(seq < 2 ** vec_dim)[0]
- idx = np.abs(idx_list - i).argmin()
- new_seq.append(seq[idx_list[idx]])
+ if len(idx_list) > 0:
+ idx = np.abs(idx_list - i).argmin()
+ new_seq.append(seq[idx_list[idx]])
+ else:
+ new_seq.append(0)
return np.row_stack([int2vec(x, vec_dim) for x in new_seq])
def post_processing(self, raw_logits: torch.Tensor, spk_num: int, output_format: str = "speaker_turn"):
@@ -244,7 +205,7 @@
ut = logits_idx.shape[1] * self.diar_model.encoder.time_ds_ratio
logits_idx = F.upsample(
logits_idx.unsqueeze(1).float(),
- size=(ut, ),
+ size=(ut,),
mode="nearest",
).squeeze(1).long()
logits_idx = logits_idx[0].tolist()
@@ -264,7 +225,7 @@
if spk not in results:
results[spk] = []
if dur > self.dur_threshold:
- results[spk].append((st, st+dur))
+ results[spk].append((st, st + dur))
# sort segments in start time ascending
for spk in results:
@@ -288,7 +249,6 @@
diarization results for each speaker
"""
- assert check_argument_types()
# Input as audio signal
if isinstance(speech, np.ndarray):
speech = torch.tensor(speech)
@@ -310,37 +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