From 74aa12ee4bbef787236bd382b186a17db40866a6 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 18 九月 2023 10:43:27 +0800
Subject: [PATCH] docs
---
funasr/bin/asr_inference_launch.py | 27 ++++++++++++++++++---------
1 files changed, 18 insertions(+), 9 deletions(-)
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index a0f21da..ea0f221 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -45,7 +45,7 @@
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
from funasr.utils.vad_utils import slice_padding_fbank
-
+from tqdm import tqdm
def inference_asr(
maxlenratio: float,
@@ -236,6 +236,7 @@
timestamp_infer_config: Union[Path, str] = None,
timestamp_model_file: Union[Path, str] = None,
param_dict: dict = None,
+ decoding_ind: int = 0,
**kwargs,
):
ncpu = kwargs.get("ncpu", 1)
@@ -290,6 +291,7 @@
nbest=nbest,
hotword_list_or_file=hotword_list_or_file,
clas_scale=clas_scale,
+ decoding_ind=decoding_ind,
)
speech2text = Speech2TextParaformer(**speech2text_kwargs)
@@ -312,6 +314,7 @@
**kwargs,
):
+ decoding_ind = None
hotword_list_or_file = None
if param_dict is not None:
hotword_list_or_file = param_dict.get('hotword')
@@ -319,6 +322,8 @@
hotword_list_or_file = kwargs['hotword']
if hotword_list_or_file is not None or 'hotword' in kwargs:
speech2text.hotword_list = speech2text.generate_hotwords_list(hotword_list_or_file)
+ if param_dict is not None and "decoding_ind" in param_dict:
+ decoding_ind = param_dict["decoding_ind"]
# 3. Build data-iterator
if data_path_and_name_and_type is None and raw_inputs is not None:
@@ -365,6 +370,7 @@
# N-best list of (text, token, token_int, hyp_object)
time_beg = time.time()
+ batch["decoding_ind"] = decoding_ind
results = speech2text(**batch)
if len(results) < 1:
hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
@@ -409,7 +415,7 @@
ibest_writer["rtf"][key] = rtf_cur
if text is not None:
- if use_timestamp and timestamp is not None:
+ if use_timestamp and timestamp is not None and len(timestamp):
postprocessed_result = postprocess_utils.sentence_postprocess(token, timestamp)
else:
postprocessed_result = postprocess_utils.sentence_postprocess(token)
@@ -421,7 +427,7 @@
else:
text_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1]
item = {'key': key, 'value': text_postprocessed}
- if timestamp_postprocessed != "":
+ if timestamp_postprocessed != "" or len(timestamp) == 0:
item['timestamp'] = timestamp_postprocessed
asr_result_list.append(item)
finish_count += 1
@@ -645,7 +651,8 @@
batch_size_token_ms_cum = 0
beg_idx = 0
- for j, _ in enumerate(range(0, n)):
+ beg_asr_total = time.time()
+ for j, _ in tqdm(enumerate(range(0, n))):
batch_size_token_ms_cum += (sorted_data[j][0][1] - sorted_data[j][0][0])
if j < n - 1 and (batch_size_token_ms_cum + sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_ms and (sorted_data[j + 1][0][1] - sorted_data[j + 1][0][0]) < batch_size_token_threshold_s:
continue
@@ -655,16 +662,17 @@
beg_idx = end_idx
batch = {"speech": speech_j, "speech_lengths": speech_lengths_j}
batch = to_device(batch, device=device)
- print("batch: ", speech_j.shape[0])
+ # print("batch: ", speech_j.shape[0])
beg_asr = time.time()
results = speech2text(**batch)
end_asr = time.time()
- print("time cost asr: ", end_asr - beg_asr)
+ # print("time cost asr: ", end_asr - beg_asr)
if len(results) < 1:
results = [["", [], [], [], [], [], []]]
results_sorted.extend(results)
-
+ end_asr_total = time.time()
+ print("total time cost asr: ", end_asr_total-beg_asr_total)
restored_data = [0] * n
for j in range(n):
index = sorted_data[j][1]
@@ -686,7 +694,7 @@
text, token, token_int = result[0], result[1], result[2]
time_stamp = result[4] if len(result[4]) > 0 else None
- if use_timestamp and time_stamp is not None:
+ if use_timestamp and time_stamp is not None and len(time_stamp):
postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
else:
postprocessed_result = postprocess_utils.sentence_postprocess(token)
@@ -711,7 +719,7 @@
item = {'key': key, 'value': text_postprocessed_punc}
if text_postprocessed != "":
item['text_postprocessed'] = text_postprocessed
- if time_stamp_postprocessed != "":
+ if time_stamp_postprocessed != "" or len(time_stamp) == 0:
item['time_stamp'] = time_stamp_postprocessed
item['sentences'] = time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed)
@@ -1816,6 +1824,7 @@
group.add_argument("--ngram_weight", type=float, default=0.9, help="ngram weight")
group.add_argument("--streaming", type=str2bool, default=False)
group.add_argument("--simu_streaming", type=str2bool, default=False)
+ group.add_argument("--full_utt", type=str2bool, default=False)
group.add_argument("--chunk_size", type=int, default=16)
group.add_argument("--left_context", type=int, default=16)
group.add_argument("--right_context", type=int, default=0)
--
Gitblit v1.9.1