[`Whisper`] Nit converting the tokenizer (#27349)

* `nospeech` instead of `nocaption` for the no speech token * oups

[`Whisper`] Nit converting the tokenizer (#27349)
* `nospeech` instead of `nocaption` for the no speech token * oups
8f840edd · Arthur · GitHub · cc9f27bb · 8f840edd
Unverified Commit 8f840edd authored Nov 07, 2023 by Arthur Committed by GitHub Nov 07, 2023
Show whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

src/transformers/models/whisper/convert_openai_to_hf.py src/transformers/models/whisper/convert_openai_to_hf.py +1 -1

No files found.
--- a/src/transformers/models/whisper/convert_openai_to_hf.py
+++ b/src/transformers/models/whisper/convert_openai_to_hf.py
@@ -235,7 +235,7 @@ def convert_tiktoken_to_hf(
        "<|transcribe|>",
        "<|startoflm|>",
        "<|startofprev|>",
-        "<|nocaptions|>",
+        "<|nospeech|>",
        "<|notimestamps|>",
    ]
    # these are special tokens, not normalized