From a836eca98e30fa67d45167dac40f359ae42d42ec Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 17 七月 2024 10:16:19 +0800
Subject: [PATCH] update
---
funasr/auto/auto_model.py | 22 +++++++++++++++-------
1 files changed, 15 insertions(+), 7 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 01e6aaf..a82f6ed 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -20,7 +20,7 @@
from funasr.download.file import download_from_url
from funasr.utils.timestamp_tools import timestamp_sentence
from funasr.utils.timestamp_tools import timestamp_sentence_en
-from funasr.download.download_from_hub import download_model
+from funasr.download.download_model_from_hub import download_model
from funasr.utils.vad_utils import slice_padding_audio_samples
from funasr.utils.vad_utils import merge_vad
from funasr.utils.load_utils import load_audio_text_image_video
@@ -121,9 +121,6 @@
log_level = getattr(logging, kwargs.get("log_level", "INFO").upper())
logging.basicConfig(level=log_level)
- if not kwargs.get("disable_log", True):
- tables.print()
-
model, kwargs = self.build_model(**kwargs)
# if vad_model is not None, build vad model else None
@@ -171,7 +168,8 @@
self.spk_kwargs = spk_kwargs
self.model_path = kwargs.get("model_path")
- def build_model(self, **kwargs):
+ @staticmethod
+ def build_model(**kwargs):
assert "model" in kwargs
if "model_conf" not in kwargs:
logging.info("download models from model hub: {}".format(kwargs.get("hub", "ms")))
@@ -217,6 +215,7 @@
kwargs["frontend"] = frontend
# build model
model_class = tables.model_classes.get(kwargs["model"])
+ assert model_class is not None, f'{kwargs["model"]} is not registered'
model_conf = {}
deep_update(model_conf, kwargs.get("model_conf", {}))
deep_update(model_conf, kwargs)
@@ -244,6 +243,10 @@
elif kwargs.get("bf16", False):
model.to(torch.bfloat16)
model.to(device)
+
+ if not kwargs.get("disable_log", True):
+ tables.print()
+
return model, kwargs
def __call__(self, *args, **cfg):
@@ -312,7 +315,7 @@
speed_stats["rtf"] = f"{(time_escape) / batch_data_time:0.3f}"
description = f"{speed_stats}, "
if pbar:
- pbar.update(1)
+ pbar.update(end_idx - beg_idx)
pbar.set_description(description)
time_speech_total += batch_data_time
time_escape_total += time_escape
@@ -336,7 +339,9 @@
# FIX(gcf): concat the vad clips for sense vocie model for better aed
if kwargs.get("merge_vad", False):
for i in range(len(res)):
- res[i]["value"] = merge_vad(res[i]["value"], kwargs.get("merge_length", 15000))
+ res[i]["value"] = merge_vad(
+ res[i]["value"], kwargs.get("merge_length_s", 15) * 1000
+ )
# step.2 compute asr model
model = self.model
@@ -377,6 +382,9 @@
if len(sorted_data) > 0 and len(sorted_data[0]) > 0:
batch_size = max(batch_size, sorted_data[0][0][1] - sorted_data[0][0][0])
+ if kwargs["device"] == "cpu":
+ batch_size = 0
+
beg_idx = 0
beg_asr_total = time.time()
time_speech_total_per_sample = speech_lengths / 16000
--
Gitblit v1.9.1