From e30a17cf4e715b3d139fa1e0ba01cda1bcf0f884 Mon Sep 17 00:00:00 2001
From: shixian.shi <shixian.shi@alibaba-inc.com>
Date: 星期三, 10 一月 2024 11:23:41 +0800
Subject: [PATCH] update funasr-onnx
---
funasr/datasets/audio_datasets/datasets.py | 24 ++++++++++++++++++++----
1 files changed, 20 insertions(+), 4 deletions(-)
diff --git a/funasr/datasets/audio_datasets/datasets.py b/funasr/datasets/audio_datasets/datasets.py
index 353a3a0..ff82856 100644
--- a/funasr/datasets/audio_datasets/datasets.py
+++ b/funasr/datasets/audio_datasets/datasets.py
@@ -8,10 +8,10 @@
import time
import logging
-from funasr.datasets.audio_datasets.load_audio_extract_fbank import load_audio, extract_fbank
-from funasr.utils.register import register_class, registry_tables
+from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
+from funasr.register import tables
-@register_class("dataset_classes", "AudioDataset")
+@tables.register("dataset_classes", "AudioDataset")
class AudioDataset(torch.utils.data.Dataset):
def __init__(self,
path,
@@ -22,8 +22,19 @@
float_pad_value: float = 0.0,
**kwargs):
super().__init__()
- index_ds_class = registry_tables.index_ds_classes.get(index_ds.lower())
+ index_ds_class = tables.index_ds_classes.get(index_ds.lower())
self.index_ds = index_ds_class(path)
+ preprocessor_speech = kwargs.get("preprocessor_speech", None)
+ if preprocessor_speech:
+ preprocessor_speech_class = tables.preprocessor_speech_classes.get(preprocessor_speech.lower())
+ preprocessor_speech = preprocessor_speech_class(**kwargs.get("preprocessor_speech_conf"))
+ self.preprocessor_speech = preprocessor_speech
+ preprocessor_text = kwargs.get("preprocessor_text", None)
+ if preprocessor_text:
+ preprocessor_text_class = tables.preprocessor_text_classes.get(preprocessor_text.lower())
+ preprocessor_text = preprocessor_text_class(**kwargs.get("preprocessor_text_conf"))
+ self.preprocessor_text = preprocessor_text
+
self.frontend = frontend
self.fs = 16000 if frontend is None else frontend.fs
self.data_type = "sound"
@@ -49,8 +60,13 @@
# pdb.set_trace()
source = item["source"]
data_src = load_audio(source, fs=self.fs)
+ if self.preprocessor_speech:
+ data_src = self.preprocessor_speech(data_src)
speech, speech_lengths = extract_fbank(data_src, data_type=self.data_type, frontend=self.frontend) # speech: [b, T, d]
+
target = item["target"]
+ if self.preprocessor_text:
+ target = self.preprocessor_text(target)
ids = self.tokenizer.encode(target)
ids_lengths = len(ids)
text, text_lengths = torch.tensor(ids, dtype=torch.int64), torch.tensor([ids_lengths], dtype=torch.int32)
--
Gitblit v1.9.1