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 | 28 +++++++++++++++++-----------
1 files changed, 17 insertions(+), 11 deletions(-)
diff --git a/funasr/bin/inference.py b/funasr/bin/inference.py
index 5b58907..2d94e70 100644
--- a/funasr/bin/inference.py
+++ b/funasr/bin/inference.py
@@ -20,6 +20,7 @@
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.utils.vad_utils import slice_padding_audio_samples
from funasr.utils.timestamp_tools import time_stamp_sentence
+from funasr.download.file import download_from_url
def prepare_data_iterator(data_in, input_len=None, data_type=None, key=None):
"""
@@ -35,7 +36,8 @@
filelist = [".scp", ".txt", ".json", ".jsonl"]
chars = string.ascii_letters + string.digits
-
+ if isinstance(data_in, str) and data_in.startswith('http'): # url
+ data_in = download_from_url(data_in)
if isinstance(data_in, str) and os.path.exists(data_in): # wav_path; filelist: wav.scp, file.jsonl;text.txt;
_, file_extension = os.path.splitext(data_in)
file_extension = file_extension.lower()
@@ -59,7 +61,7 @@
data_list = [data_in]
key_list = [key]
elif isinstance(data_in, (list, tuple)):
- if data_type is not None and isinstance(data_type, (list, tuple)):
+ if data_type is not None and isinstance(data_type, (list, tuple)): # mutiple inputs
data_list_tmp = []
for data_in_i, data_type_i in zip(data_in, data_type):
key_list, data_list_i = prepare_data_iterator(data_in=data_in_i, data_type=data_type_i)
@@ -68,7 +70,7 @@
for item in zip(*data_list_tmp):
data_list.append(item)
else:
- # [audio sample point, fbank]
+ # [audio sample point, fbank, text]
data_list = data_in
key_list = ["rand_key_" + ''.join(random.choice(chars) for _ in range(13)) for _ in range(len(data_in))]
else: # raw text; audio sample point, fbank; bytes
@@ -157,6 +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)
@@ -168,8 +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)
@@ -198,13 +202,12 @@
kwargs = self.kwargs if kwargs is None else kwargs
kwargs.update(cfg)
model = self.model if model is None else model
-
- data_type = kwargs.get("data_type", "sound")
+
batch_size = kwargs.get("batch_size", 1)
# if kwargs.get("device", "cpu") == "cpu":
# batch_size = 1
- key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=data_type, key=key)
+ key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=kwargs.get("data_type", None), key=key)
speed_stats = {}
asr_result_list = []
@@ -268,8 +271,8 @@
batch_size = int(kwargs.get("batch_size_s", 300))*1000
batch_size_threshold_ms = int(kwargs.get("batch_size_threshold_s", 60))*1000
kwargs["batch_size"] = batch_size
- data_type = kwargs.get("data_type", "sound")
- key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=data_type)
+
+ key_list, data_list = prepare_data_iterator(input, input_len=input_len, data_type=kwargs.get("data_type", None))
results_ret_list = []
time_speech_total_all_samples = 0.0
@@ -390,7 +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):
@@ -422,7 +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