From 71b38b1c2c3bc4a2cf6ffac700ba07c5da969dbe Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 19 九月 2023 12:32:02 +0800
Subject: [PATCH] wechat
---
funasr/bin/asr_inference_launch.py | 16 ++++++++--------
1 files changed, 8 insertions(+), 8 deletions(-)
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index ea0f221..ad657eb 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -427,7 +427,7 @@
else:
text_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1]
item = {'key': key, 'value': text_postprocessed}
- if timestamp_postprocessed != "" or len(timestamp) == 0:
+ if timestamp_postprocessed != "":
item['timestamp'] = timestamp_postprocessed
asr_result_list.append(item)
finish_count += 1
@@ -652,7 +652,7 @@
batch_size_token_ms_cum = 0
beg_idx = 0
beg_asr_total = time.time()
- for j, _ in tqdm(enumerate(range(0, n))):
+ for j, _ in enumerate(tqdm(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
@@ -719,7 +719,7 @@
item = {'key': key, 'value': text_postprocessed_punc}
if text_postprocessed != "":
item['text_postprocessed'] = text_postprocessed
- if time_stamp_postprocessed != "" or len(time_stamp) == 0:
+ if time_stamp_postprocessed != "":
item['time_stamp'] = time_stamp_postprocessed
item['sentences'] = time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed)
@@ -1297,7 +1297,7 @@
quantize_modules: Optional[List[str]] = None,
quantize_dtype: Optional[str] = "float16",
streaming: Optional[bool] = False,
- simu_streaming: Optional[bool] = False,
+ fake_streaming: Optional[bool] = False,
full_utt: Optional[bool] = False,
chunk_size: Optional[int] = 16,
left_context: Optional[int] = 16,
@@ -1374,7 +1374,7 @@
quantize_modules=quantize_modules,
quantize_dtype=quantize_dtype,
streaming=streaming,
- simu_streaming=simu_streaming,
+ fake_streaming=fake_streaming,
full_utt=full_utt,
chunk_size=chunk_size,
left_context=left_context,
@@ -1432,8 +1432,8 @@
final_hyps = speech2text.streaming_decode(
speech[_end: len(speech)], is_final=True
)
- elif speech2text.simu_streaming:
- final_hyps = speech2text.simu_streaming_decode(**batch)
+ elif speech2text.fake_streaming:
+ final_hyps = speech2text.fake_streaming_decode(**batch)
elif speech2text.full_utt:
final_hyps = speech2text.full_utt_decode(**batch)
else:
@@ -1823,7 +1823,7 @@
group.add_argument("--lm_weight", type=float, default=1.0, help="RNNLM weight")
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("--fake_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)
--
Gitblit v1.9.1