diff --git a/faster_whisper/tokenizer.py b/faster_whisper/tokenizer.py
index 3bf76a5..d75bbd7 100644
--- a/faster_whisper/tokenizer.py
+++ b/faster_whisper/tokenizer.py
@@ -67,6 +67,12 @@ class Tokenizer:
     def no_timestamps(self) -> int:
         return self.tokenizer.token_to_id("<|notimestamps|>")
 
+    @cached_property
+    def no_speech(self) -> int:
+        return self.tokenizer.token_to_id("<|nospeech|>") or self.tokenizer.token_to_id(
+            "<|nocaptions|>"
+        )
+
     @property
     def timestamp_begin(self) -> int:
         return self.no_timestamps + 1
diff --git a/faster_whisper/transcribe.py b/faster_whisper/transcribe.py
index a73b31b..6e57ff7 100644
--- a/faster_whisper/transcribe.py
+++ b/faster_whisper/transcribe.py
@@ -1886,6 +1886,7 @@ def get_suppressed_tokens(
             tokenizer.sot,
             tokenizer.sot_prev,
             tokenizer.sot_lm,
+            tokenizer.no_speech,
         ]
     )
 
diff --git a/tests/test_tokenizer.py b/tests/test_tokenizer.py
index 5ea43b0..1a1e27b 100644
--- a/tests/test_tokenizer.py
+++ b/tests/test_tokenizer.py
@@ -98,6 +98,7 @@ def test_suppressed_tokens_minus_1():
         50358,
         50359,
         50360,
+        50361,
     )
 
 
@@ -106,7 +107,7 @@ def test_suppressed_tokens_minus_value():
 
     tokenizer = Tokenizer(model.hf_tokenizer, False)
     tokens = get_suppressed_tokens(tokenizer, [13])
-    assert tokens == (13, 50257, 50357, 50358, 50359, 50360)
+    assert tokens == (13, 50257, 50357, 50358, 50359, 50360, 50361)
 
 
 def test_split_on_unicode():