suppress_tokens=[] should be legal as some older. whisper models rely on this

[Lewington-pitsos]

System Info

• transformers version: 4.46.0
• Platform: macOS-15.2-arm64-arm-64bit
• Python version: 3.11.8
• Huggingface_hub version: 0.25.2
• Safetensors version: 0.4.2
• Accelerate version: not installed
• Accelerate config: not found
• PyTorch version (GPU?): 2.2.1 (False)
• Tensorflow version (GPU?): 2.16.1 (False)
• Flax version (CPU?/GPU?/TPU?): not installed (NA)
• Jax version: not installed
• JaxLib version: not installed

Who can help?

I'm intending to fix this at once

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

Run this code

import torch

from transformers import pipeline

# path to the audio file to be transcribed

audio = "/path/to/audio.format"

device = "cuda:0" if torch.cuda.is_available() else "cpu"

transcribe = pipeline(task="automatic-speech-recognition", model="vasista22/whisper-tamil-large-v2", chunk_length_s=30, device=device)

transcribe.model.config.forced_decoder_ids = transcribe.tokenizer.get_decoder_prompt_ids(language="ta", task="transcribe")

print('Transcription: ', transcribe(audio)["text"])

on any machine

Expected behavior

The model produces a prediction, and no error is thrown

What actually happens is I get

/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/models/whisper/generation_whisper.py:573: FutureWarning: The input name `inputs` is deprecated. Please make sure to use `input_features` instead.
  warnings.warn(
Traceback (most recent call last):
  File "/Users/plato/code/translation-station/pad.py", line 11, in <module>
    print('Transcription: ', transcribe(audio)["text"])
                             ^^^^^^^^^^^^^^^^^
  File "/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 283, in __call__
    return super().__call__(inputs, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/pipelines/base.py", line 1360, in __call__
    return next(
           ^^^^^
  File "/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/pipelines/pt_utils.py", line 124, in __next__
    item = next(self.iterator)
           ^^^^^^^^^^^^^^^^^^^
  File "/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/pipelines/pt_utils.py", line 269, in __next__
    processed = self.infer(next(self.iterator), **self.params)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/pipelines/base.py", line 1275, in forward
    model_outputs = self._forward(model_inputs, **forward_params)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/pipelines/automatic_speech_recognition.py", line 521, in _forward
    tokens = self.model.generate(
             ^^^^^^^^^^^^^^^^^^^^
  File "/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/models/whisper/generation_whisper.py", line 739, in generate
    decoder_input_ids, kwargs = self._prepare_decoder_input_ids(
                                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/plato/code/translation-station/.venv/lib/python3.11/site-packages/transformers/models/whisper/generation_whisper.py", line 1782, in _prepare_decoder_input_ids
    prev_start_of_text = suppress_tokens[-2] if suppress_tokens is not None else None
                         ~~~~~~~~~~~~~~~^^^^
IndexError: index -2 is out of bounds for dimension 0 with size 0

this exact same error was noticed on some other models posted on huggingface by https://huggingface.co/vasista22 around 2 years ago, for example https://huggingface.co/vasista22/whisper-tamil-large-v2/discussions/4 and https://huggingface.co/vasista22/whisper-hindi-small/discussions/7