Fix Whisper Conversion Script: Correct decoder_attention_heads and _download function (#26834)

* Fix error in convert_openai_to_hf.py: "_download() missing 1 required positional argument: root"

* Fix error in convert_openai_to_hf.py: "TypeError: byte indices must be integers or slices, not str"

* Fix decoder_attention_heads value in convert_openai_to_hf.py.

Correct the assignment for `decoder_attention_heads` in the conversion script for the Whisper model.

* Black reformat convert_openai_to_hf.py file.

* Fix Whisper model configuration defaults (for Tiny).

- Correct encoder/decoder layers and attention heads count.
- Update model width (`d_model`) to 384.

* Add docstring to the convert_openai_to_hf.py script with a doctest

* Add shebang and +x permission to the convert_openai_to_hf.py

* convert_openai_to_hf.py: reuse the read model_bytes in the _download() function

* Move convert_openai_to_hf.py doctest example to whisper.md

* whisper.md: Add an inference example to the Conversion section.

* whisper.md: remove `model.config.forced_decoder_ids` from examples (deprecated)

* whisper.md: Remove "## Format Conversion" section; not used by users

* whisper.md: Use librispeech_asr_dummy dataset and load_dataset()

docs/source/en/model_doc/whisper.md

@@ -34,6 +34,42 @@ The original code can be found [here](https://github.com/openai/whisper).
 - Inference is currently only implemented for short-form i.e. audio is pre-segmented into <=30s segments. Long-form (including timestamps) will be implemented in a future release.
 - One can use [`WhisperProcessor`] to prepare audio for the model, and decode the predicted ID's back into text.
 
+This model was contributed by [Arthur Zucker](https://huggingface.co/ArthurZ). The Tensorflow version of this model was contributed by [amyeroberts](https://huggingface.co/amyeroberts).
+The original code can be found [here](https://github.com/openai/whisper).
+
+## Inference
+
+Here is a step-by-step guide to transcribing an audio sample using a pre-trained Whisper model:
+
+```python
+>>> from datasets import load_dataset
+>>> from transformers import WhisperProcessor, WhisperForConditionalGeneration
+
+>>> # Select an audio file and read it:
+>>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
+>>> audio_sample = ds[0]["audio"]
+>>> waveform = audio_sample["array"]
+>>> sampling_rate = audio_sample["sampling_rate"]
+
+>>> # Load the Whisper model in Hugging Face format:
+>>> processor = WhisperProcessor.from_pretrained("openai/whisper-tiny.en")
+>>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-tiny.en")
+
+>>> # Use the model and processor to transcribe the audio:
+>>> input_features = processor(
+...     waveform, sampling_rate=sampling_rate, return_tensors="pt"
+... ).input_features
+
+>>> # Generate token ids
+>>> predicted_ids = model.generate(input_features)
+
+>>> # Decode token ids to text
+>>> transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+
+>>> transcription[0]
+' Mr. Quilter is the apostle of the middle classes, and we are glad to welcome his gospel.'
+```
+
 ## WhisperConfig
 
 [[autodoc]] WhisperConfig