From 6728db5b59d4aa26424400a6c420036b98cca726 Mon Sep 17 00:00:00 2001
From: zxcd <228587199@qq.com>
Date: Thu, 9 Feb 2023 10:51:23 +0800
Subject: [PATCH] [ASR]Whisper remove audio duration limit, test=asr (#2900)

---
 paddlespeech/cli/whisper/infer.py            | 9 +--------
 paddlespeech/s2t/models/whisper/__init__.py  | 2 +-
 paddlespeech/s2t/models/whisper/tokenizer.py | 2 +-
 paddlespeech/s2t/models/whisper/utils.py     | 2 +-
 paddlespeech/s2t/models/whisper/whipser.py   | 2 +-
 5 files changed, 5 insertions(+), 12 deletions(-)

diff --git a/paddlespeech/cli/whisper/infer.py b/paddlespeech/cli/whisper/infer.py
index c016b453ade..ebcca890b59 100644
--- a/paddlespeech/cli/whisper/infer.py
+++ b/paddlespeech/cli/whisper/infer.py
@@ -152,8 +152,7 @@ def _init_from_path(self,
         Init model and other resources from a specific path.
         """
         logger.debug("start to init the model")
-        # default max_len: unit:second
-        self.max_len = 50
+
         if hasattr(self, 'model'):
             logger.debug('Model had been initialized.')
             return
@@ -339,12 +338,6 @@ def _check(self, audio_file: str, sample_rate: int, force_yes: bool=False):
         try:
             audio, audio_sample_rate = soundfile.read(
                 audio_file, dtype="int16", always_2d=True)
-            audio_duration = audio.shape[0] / audio_sample_rate
-            if audio_duration > self.max_len:
-                logger.error(
-                    f"Please input audio file less then {self.max_len} seconds.\n"
-                )
-                return False
         except Exception as e:
             logger.exception(e)
             logger.error(
diff --git a/paddlespeech/s2t/models/whisper/__init__.py b/paddlespeech/s2t/models/whisper/__init__.py
index 98ab2361086..b78dece8aaa 100644
--- a/paddlespeech/s2t/models/whisper/__init__.py
+++ b/paddlespeech/s2t/models/whisper/__init__.py
@@ -1,5 +1,5 @@
 # MIT License, Copyright (c) 2022 OpenAI.
-# Copyright (c) 2022 PaddlePaddle Authors and . All Rights Reserved.
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
 # 
 # Modified from OpenAI Whisper 2022 (https://github.com/openai/whisper/whisper/__init__.py)
 from paddlespeech.s2t.models.whisper.whipser import decode
diff --git a/paddlespeech/s2t/models/whisper/tokenizer.py b/paddlespeech/s2t/models/whisper/tokenizer.py
index 1e1aea044d1..e8b201bcc6f 100644
--- a/paddlespeech/s2t/models/whisper/tokenizer.py
+++ b/paddlespeech/s2t/models/whisper/tokenizer.py
@@ -1,5 +1,5 @@
 # MIT License, Copyright (c) 2022 OpenAI.
-# Copyright (c) 2022 PaddlePaddle Authors and . All Rights Reserved.
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
 # 
 # Modified from OpenAI Whisper 2022 (https://github.com/openai/whisper/whisper/tokenizer.py)
 import os
diff --git a/paddlespeech/s2t/models/whisper/utils.py b/paddlespeech/s2t/models/whisper/utils.py
index d067af7d2b6..5528f9604ac 100644
--- a/paddlespeech/s2t/models/whisper/utils.py
+++ b/paddlespeech/s2t/models/whisper/utils.py
@@ -1,5 +1,5 @@
 # MIT License, Copyright (c) 2022 OpenAI.
-# Copyright (c) 2022 PaddlePaddle Authors and . All Rights Reserved.
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
 # 
 # Modified from OpenAI Whisper 2022 (https://github.com/openai/whisper/whisper/utils.py)
 import zlib
diff --git a/paddlespeech/s2t/models/whisper/whipser.py b/paddlespeech/s2t/models/whisper/whipser.py
index 9cf9a9ecab4..a28013e4b9a 100644
--- a/paddlespeech/s2t/models/whisper/whipser.py
+++ b/paddlespeech/s2t/models/whisper/whipser.py
@@ -1,5 +1,5 @@
 # MIT License, Copyright (c) 2022 OpenAI.
-# Copyright (c) 2022 PaddlePaddle Authors and . All Rights Reserved.
+# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
 #
 # Modified from OpenAI Whisper 2022 (https://github.com/openai/whisper/whisper)
 import os