From e9d2cfc3a134b00f4e98271fbee3838d1ccecbcc Mon Sep 17 00:00:00 2001
From: VirtuosoQ <2416050435@qq.com>
Date: 星期五, 26 四月 2024 14:59:30 +0800
Subject: [PATCH] FunASR java http client
---
funasr/models/paraformer/model.py | 34 +++++++++++++++++++++++-----------
1 files changed, 23 insertions(+), 11 deletions(-)
diff --git a/funasr/models/paraformer/model.py b/funasr/models/paraformer/model.py
index 6e422ad..6c7957c 100644
--- a/funasr/models/paraformer/model.py
+++ b/funasr/models/paraformer/model.py
@@ -13,13 +13,14 @@
from funasr.models.ctc.ctc import CTC
from funasr.utils import postprocess_utils
from funasr.metrics.compute_acc import th_accuracy
+from funasr.train_utils.device_funcs import to_device
from funasr.utils.datadir_writer import DatadirWriter
from funasr.models.paraformer.search import Hypothesis
from funasr.models.paraformer.cif_predictor import mae_loss
from funasr.train_utils.device_funcs import force_gatherable
from funasr.losses.label_smoothing_loss import LabelSmoothingLoss
from funasr.models.transformer.utils.add_sos_eos import add_sos_eos
-from funasr.models.transformer.utils.nets_utils import make_pad_mask, pad_list
+from funasr.models.transformer.utils.nets_utils import make_pad_mask
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
@@ -154,8 +155,8 @@
self.predictor_bias = predictor_bias
self.sampling_ratio = sampling_ratio
self.criterion_pre = mae_loss(normalize_length=length_normalized_loss)
- # self.step_cur = 0
- #
+
+
self.share_embedding = share_embedding
if self.share_embedding:
self.decoder.embed = None
@@ -180,15 +181,12 @@
text: (Batch, Length)
text_lengths: (Batch,)
"""
- # import pdb;
- # pdb.set_trace()
if len(text_lengths.size()) > 1:
text_lengths = text_lengths[:, 0]
if len(speech_lengths.size()) > 1:
speech_lengths = speech_lengths[:, 0]
batch_size = speech.shape[0]
-
# Encoder
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
@@ -230,6 +228,7 @@
stats["loss_pre"] = loss_pre.detach().cpu() if loss_pre is not None else None
stats["loss"] = torch.clone(loss.detach())
+ stats["batch_size"] = batch_size
# force_gatherable: to-device and to-tensor if scalar for DataParallel
if self.length_normalized_loss:
@@ -455,7 +454,9 @@
speech, speech_lengths = data_in, data_lengths
if len(speech.shape) < 3:
speech = speech[None, :, :]
- if speech_lengths is None:
+ if speech_lengths is not None:
+ speech_lengths = speech_lengths.squeeze(-1)
+ else:
speech_lengths = speech.shape[1]
else:
# extract fbank feats
@@ -471,6 +472,8 @@
speech = speech.to(device=kwargs["device"])
speech_lengths = speech_lengths.to(device=kwargs["device"])
# Encoder
+ if kwargs.get("fp16", False):
+ speech = speech.half()
encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
if isinstance(encoder_out, tuple):
encoder_out = encoder_out[0]
@@ -491,6 +494,8 @@
b, n, d = decoder_out.size()
if isinstance(key[0], (list, tuple)):
key = key[0]
+ if len(key) < b:
+ key = key*b
for i in range(b):
x = encoder_out[i, :encoder_out_lens[i], :]
am_scores = decoder_out[i, :pre_token_length[i], :]
@@ -512,9 +517,10 @@
nbest_hyps = [Hypothesis(yseq=yseq, score=score)]
for nbest_idx, hyp in enumerate(nbest_hyps):
ibest_writer = None
- if ibest_writer is None and kwargs.get("output_dir") is not None:
- writer = DatadirWriter(kwargs.get("output_dir"))
- ibest_writer = writer[f"{nbest_idx+1}best_recog"]
+ if kwargs.get("output_dir") is not None:
+ if not hasattr(self, "writer"):
+ self.writer = DatadirWriter(kwargs.get("output_dir"))
+ ibest_writer = self.writer[f"{nbest_idx+1}best_recog"]
# remove sos/eos and get results
last_pos = -1
if isinstance(hyp.yseq, list):
@@ -534,7 +540,6 @@
result_i = {"key": key[i], "text": text_postprocessed}
-
if ibest_writer is not None:
ibest_writer["token"][key[i]] = " ".join(token)
# ibest_writer["text"][key[i]] = text
@@ -545,3 +550,10 @@
return results, meta_data
+ def export(self, **kwargs):
+ from .export_meta import export_rebuild_model
+ if 'max_seq_len' not in kwargs:
+ kwargs['max_seq_len'] = 512
+ models = export_rebuild_model(model=self, **kwargs)
+ return models
+
--
Gitblit v1.9.1