Fix/pyannote ollama

[Gambitnl]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @Gambitnl, 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 enhances the stability and user experience of the audio processing pipeline. It addresses critical issues in both the PyAnnote speaker diarization and Ollama-based classification components, making them more resilient to common failure modes like memory exhaustion and API changes. Furthermore, it introduces a live transcription preview feature, providing users with immediate feedback and greater transparency during lengthy processing tasks.

Highlights

• Enhanced Ollama Stability: Implemented robust retry mechanisms for Ollama classification, including low-VRAM settings and an optional fallback model, to prevent memory exhaustion crashes and improve reliability.
• PyAnnote Diarization Resilience: Fixed speaker embedding extraction issues in PyAnnote 3.x by normalizing embedding outputs to NumPy arrays and adding error handling to prevent diarization failures.
• Live Transcription Preview: Introduced a real-time transcription preview in the Gradio UI, allowing users to monitor chunk-level progress and verify transcription quality during long processing sessions.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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 introduces several significant improvements. It fixes a crash in PyAnnote embedding extraction by making the normalization more robust and adding error handling. It also addresses Ollama memory exhaustion issues by implementing a retry mechanism with low-VRAM settings and an optional fallback model, along with a preflight check to warn users about potential memory issues. Additionally, a new live transcription preview feature has been added to the UI, providing real-time feedback during processing. The changes are well-structured and include corresponding updates to documentation and tests. I've found one area for improvement regarding exception handling to make the code even more robust.

[gemini-code-assist]

The try...except Exception: blocks used for psutil and ctypes are too broad and can hide unexpected errors. It's better to catch specific exceptions that you expect to handle. For example, psutil might fail to import, or virtual_memory() could raise an OSError. Catching Exception could swallow bugs and make debugging harder.

    def _estimate_total_memory_gb(self) -> Optional[float]:
        bytes_per_gb = 1024 ** 3
        try:
            import psutil  # type: ignore

            return psutil.virtual_memory().total / bytes_per_gb
        except (ImportError, AttributeError, OSError):
            pass

        if hasattr(os, "sysconf"):
            try:
                page_size = os.sysconf("SC_PAGE_SIZE")
                phys_pages = os.sysconf("SC_PHYS_PAGES")
                if isinstance(page_size, int) and isinstance(phys_pages, int):
                    return (page_size * phys_pages) / bytes_per_gb
            except (ValueError, OSError, AttributeError):
                pass

        if os.name == "nt":
            try:
                import ctypes

                class MEMORYSTATUSEX(ctypes.Structure):
                    _fields_: List[tuple[str, Any]] = [
                        ("dwLength", ctypes.c_ulong),
                        ("dwMemoryLoad", ctypes.c_ulong),
                        ("ullTotalPhys", ctypes.c_ulonglong),
                        ("ullAvailPhys", ctypes.c_ulonglong),
                        ("ullTotalPageFile", ctypes.c_ulonglong),
                        ("ullAvailPageFile", ctypes.c_ulonglong),
                        ("ullTotalVirtual", ctypes.c_ulonglong),
                        ("ullAvailVirtual", ctypes.c_ulonglong),
                        ("ullAvailExtendedVirtual", ctypes.c_ulonglong),
                    ]

                status = MEMORYSTATUSEX()
                status.dwLength = ctypes.sizeof(MEMORYSTATUSEX)
                if ctypes.windll.kernel32.GlobalMemoryStatusEx(ctypes.byref(status)):
                    return float(status.ullTotalPhys) / bytes_per_gb
            except (ImportError, AttributeError, OSError):
                pass

        return None