Remove model_name param from Whisper-Metal

[seyeong-han]

Issue

I found that the tokenizer was wrong when I run open-ai/whisper-tiny model using whisper_runner by looking at the transcription result.

• Expected

<\|en\|><\|transcribe\|><\|notimestamps\|> This week, I traveled to Chicago to deliver my final farewell address to the nation, following in the tradition of presidents before me. It was not opportunity to say thank you. Whether we've seen IDI or rarely agreed at all, my conversations with you, the American people, in living rooms and schools,<\|endoftext\|>

• Result

<|startoftranscript|><|translate|><|10.00|> So.<|24.00|><|endoftext|>

Since HuggingFace has updated all Whisper model tokenizers to the v3 format, we don't need to care about the decoder_start_token_id manually.

Solution

• Removed model_name argument from run.sh and main.cpp
• Hardcoded decoder_start_token_id=50258 for all models
• Fixes tokenizer compatibility issue where all Whisper models from HuggingFace now use the v3 tokenizer format
• Eliminates confusion about which model name to pass at runtime

@manuelcandales

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15798

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit ed8786f with merge base ed72daf ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[seyeong-han]

@pytorchbot label "release notes: desktop"