Omit space prefix in initial_prompt for spaceless languages.

openai · Mar 31, 2024 · 21999e1 · 21999e1
1 parent ba3f3cd
commit 21999e1
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/whisper/transcribe.py b/whisper/transcribe.py
@@ -228,7 +228,8 @@ def decode_with_fallback(segment: torch.Tensor) -> DecodingResult:
     prompt_reset_since = 0
 
     if initial_prompt is not None:
-        initial_prompt_tokens = tokenizer.encode(" " + initial_prompt.strip())
+        space = "" if language in {"zh", "ja", "th", "lo", "my", "yue"} else " "
+        initial_prompt_tokens = tokenizer.encode(space + initial_prompt.strip())
         all_tokens.extend(initial_prompt_tokens)
     else:
         initial_prompt_tokens = []