From 78ffd04ac9c6e4024c751dc844768d55375fba91 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 11 一月 2024 00:10:50 +0800
Subject: [PATCH] Merge branch 'funasr1.0' of github.com:alibaba-damo-academy/FunASR into funasr1.0 add
---
funasr/bin/inference.py | 11 ++++++++---
1 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/funasr/bin/inference.py b/funasr/bin/inference.py
index dedaf7d..2d94e70 100644
--- a/funasr/bin/inference.py
+++ b/funasr/bin/inference.py
@@ -159,6 +159,9 @@
tokenizer = tokenizer_class(**kwargs["tokenizer_conf"])
kwargs["tokenizer"] = tokenizer
kwargs["token_list"] = tokenizer.token_list
+ vocab_size = len(tokenizer.token_list)
+ else:
+ vocab_size = -1
# build frontend
frontend = kwargs.get("frontend", None)
@@ -170,8 +173,7 @@
# build model
model_class = tables.model_classes.get(kwargs["model"].lower())
- model = model_class(**kwargs, **kwargs["model_conf"],
- vocab_size=len(tokenizer.token_list) if tokenizer is not None else -1)
+ model = model_class(**kwargs, **kwargs["model_conf"], vocab_size=vocab_size)
model.eval()
model.to(device)
@@ -391,7 +393,10 @@
frontend = frontend_class(**kwargs["frontend_conf"])
self.frontend = frontend
+ if "frontend" in kwargs:
+ del kwargs["frontend"]
self.kwargs = kwargs
+
def __call__(self, input, input_len=None, kwargs=None, **cfg):
@@ -423,7 +428,7 @@
time2 = time.perf_counter()
meta_data["load_data"] = f"{time2 - time1:0.3f}"
speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),
- frontend=self.frontend)
+ frontend=self.frontend, **kwargs)
time3 = time.perf_counter()
meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
meta_data["batch_data_time"] = speech_lengths.sum().item() * self.frontend.frame_shift * self.frontend.lfr_n / 1000
--
Gitblit v1.9.1