[Frontend] Generalize v1/audio/transcriptions endpoint

[NickLucche]

Anticipating more models like Gemma3n with audio as input, this PR attempts to make the transcription endpoint a bit more general whle moving some of the whisper specifics into SupportsTranscription.
It's the first step in opening up v1/audio/transcriptions to models other than whisper, while untangling some of the whisper hard-coded values.

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist]

Summary of Changes

Hello @NickLucche, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly refactors the v1/audio/transcriptions endpoint to enhance its generality and support for diverse audio models beyond Whisper. It achieves this by abstracting Whisper-specific logic into the WhisperModel class, which now implements new methods defined in the SupportsTranscription protocol. This change paves the way for easier integration of new audio transcription models like Gemma3n, by centralizing model-specific configurations and behaviors.

Highlights

• Endpoint Generalization: The v1/audio/transcriptions endpoint has been refactored to remove Whisper-specific hardcoded values, making it more general and extensible for future audio models.
• Abstraction of Model-Specific Logic: Whisper-specific configurations and behaviors, such as supported languages, decoder prompt formatting, and audio chunking parameters, have been moved from the speech_to_text.py entrypoint into the WhisperModel class, adhering to the SupportsTranscription protocol.
• Enhanced SupportsTranscription Protocol: The vllm/model_executor/models/interfaces.py file now includes new class methods (get_decoder_prompt, get_supported_languages, supports_language) within the SupportsTranscription protocol, providing a standardized interface for audio transcription models.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request generalizes the /v1/audio/transcriptions endpoint by introducing a SupportsTranscription protocol and moving Whisper-specific logic into the WhisperForConditionalGeneration model. There is a critical bug related to f-string formatting that would cause incorrect prompt generation, and a medium-severity suggestion to improve code style.

[DarkLight1337]

We just need either get_supported_languages or supports_language. For custom error handling, perhaps we could merge them into a single method, validate_language(input_language)

[huytuong010101]

waiting for this

[huytuong010101]

@NickLucche By this PR we can use at v1/audio/transcriptions endpoint? Can we customize the prompt via request?