From 0d32e02c79d751ae15af8fb767df32564e34cbf7 Mon Sep 17 00:00:00 2001
From: 语帆 <yf352572@alibaba-inc.com>
Date: 星期三, 28 二月 2024 14:02:03 +0800
Subject: [PATCH] test
---
funasr/models/lcbnet/model.py | 50 ++++++++++++++++++++++++++++++++++++++++++++------
1 files changed, 44 insertions(+), 6 deletions(-)
diff --git a/funasr/models/lcbnet/model.py b/funasr/models/lcbnet/model.py
index c68ccd7..1acce78 100644
--- a/funasr/models/lcbnet/model.py
+++ b/funasr/models/lcbnet/model.py
@@ -1,3 +1,8 @@
+#!/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 logging
from typing import Union, Dict, List, Tuple, Optional
@@ -16,11 +21,14 @@
from funasr.utils import postprocess_utils
from funasr.utils.datadir_writer import DatadirWriter
from funasr.register import tables
-
-@tables.register("model_classes", "Transformer")
-class Transformer(nn.Module):
- """CTC-attention hybrid Encoder-Decoder model"""
-
+import pdb
+@tables.register("model_classes", "LCBNet")
+class LCBNet(nn.Module):
+ """
+ Author: Speech Lab of DAMO Academy, Alibaba Group
+ LCB-NET: LONG-CONTEXT BIASING FOR AUDIO-VISUAL SPEECH RECOGNITION
+ https://arxiv.org/abs/2401.06390
+ """
def __init__(
self,
@@ -32,10 +40,19 @@
encoder_conf: dict = None,
decoder: str = None,
decoder_conf: dict = None,
+ text_encoder: str = None,
+ text_encoder_conf: dict = None,
+ bias_predictor: str = None,
+ bias_predictor_conf: dict = None,
+ fusion_encoder: str = None,
+ fusion_encoder_conf: dict = None,
ctc: str = None,
ctc_conf: dict = None,
ctc_weight: float = 0.5,
interctc_weight: float = 0.0,
+ select_num: int = 2,
+ select_length: int = 3,
+ insert_blank: bool = True,
input_size: int = 80,
vocab_size: int = -1,
ignore_id: int = -1,
@@ -66,6 +83,15 @@
encoder_class = tables.encoder_classes.get(encoder)
encoder = encoder_class(input_size=input_size, **encoder_conf)
encoder_output_size = encoder.output_size()
+
+ # lcbnet modules: text encoder, fusion encoder and bias predictor
+ text_encoder_class = tables.encoder_classes.get(text_encoder)
+ text_encoder = text_encoder_class(input_size=vocab_size, **text_encoder_conf)
+ fusion_encoder_class = tables.encoder_classes.get(fusion_encoder)
+ fusion_encoder = fusion_encoder_class(**fusion_encoder_conf)
+ bias_predictor_class = tables.encoder_classes.get(bias_predictor)
+ bias_predictor = bias_predictor_class(**bias_predictor_conf)
+
if decoder is not None:
decoder_class = tables.decoder_classes.get(decoder)
decoder = decoder_class(
@@ -91,6 +117,13 @@
self.specaug = specaug
self.normalize = normalize
self.encoder = encoder
+ # lcbnet
+ self.text_encoder = text_encoder
+ self.fusion_encoder = fusion_encoder
+ self.bias_predictor = bias_predictor
+ self.select_num = select_num
+ self.select_length = select_length
+ self.insert_blank = insert_blank
if not hasattr(self.encoder, "interctc_use_conditioning"):
self.encoder.interctc_use_conditioning = False
@@ -391,13 +424,18 @@
else:
# extract fbank feats
time1 = time.perf_counter()
- audio_sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000),
+ pdb.set_trace()
+ sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000),
data_type=kwargs.get("data_type", "sound"),
tokenizer=tokenizer)
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
+ audio_sample_list = sample_list[0]
+ ocr_sample_list = sample_list[1]
+ pdb.set_trace()
speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
frontend=frontend)
+ pdb.set_trace()
time3 = time.perf_counter()
meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
meta_data["batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000
--
Gitblit v1.9.1