From b9bcf1f093c3053fdc4e2cf4a1d38e27bbf429fb Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 19 十月 2023 14:03:48 +0800
Subject: [PATCH] docs
---
funasr/bin/asr_infer.py | 7 ++++---
egs_modelscope/asr/TEMPLATE/README_zh.md | 2 +-
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/egs_modelscope/asr/TEMPLATE/README_zh.md b/egs_modelscope/asr/TEMPLATE/README_zh.md
index c5829a5..cdafddd 100644
--- a/egs_modelscope/asr/TEMPLATE/README_zh.md
+++ b/egs_modelscope/asr/TEMPLATE/README_zh.md
@@ -38,7 +38,7 @@
batch_size_token=5000, batch_size_token_threshold_s=40, max_single_segment_time=6000)
print(rec_result)
```
-Where,
+鍏朵腑锛�
- `batch_size_token` 琛ㄧず閲囩敤鍔ㄦ�乥atch锛宐atch涓�籺oken鏁颁负 `batch_size_token`锛�1 token = 60 ms.
- `batch_size_token_threshold_s`: 琛ㄧず闊抽鏃堕暱瓒呰繃 `batch_size_token_threshold_s`闃堝�兼槸锛宐atch鏁拌缃负1, 鍗曚綅涓簊.
- `max_single_segment_time`: 琛ㄧずVAD鏈�澶у垏鍓查煶棰戞椂闀�, 鍗曚綅鏄痬s.
diff --git a/funasr/bin/asr_infer.py b/funasr/bin/asr_infer.py
index ef3ed6e..4648fb3 100644
--- a/funasr/bin/asr_infer.py
+++ b/funasr/bin/asr_infer.py
@@ -1922,9 +1922,6 @@
):
from funasr.tasks.whisper import ASRTask
- from funasr.utils.whisper_utils.transcribe import transcribe
- from funasr.utils.whisper_utils.audio import pad_or_trim, log_mel_spectrogram
- from funasr.utils.whisper_utils.decoding import DecodingOptions, detect_language, decode
# 1. Build ASR model
scorers = {}
@@ -1987,6 +1984,10 @@
"""
+ from funasr.utils.whisper_utils.transcribe import transcribe
+ from funasr.utils.whisper_utils.audio import pad_or_trim, log_mel_spectrogram
+ from funasr.utils.whisper_utils.decoding import DecodingOptions, detect_language, decode
+
speech = speech[0]
speech = pad_or_trim(speech)
mel = log_mel_spectrogram(speech).to(self.device)
--
Gitblit v1.9.1