Skip to main content

Mistral Voxtral plugin for the cjm-transcription-plugin-system library - provides local speech-to-text transcription through 🤗 Transformers with configurable model selection and parameter control.

Project description

cjm-transcription-plugin-voxtral-hf

Install

pip install cjm_transcription_plugin_voxtral_hf

Project Structure

nbs/
└── plugin.ipynb # Plugin implementation for Mistral Voxtral transcription through Hugging Face Transformers

Total: 1 notebook

Module Dependencies

graph LR
    plugin[plugin<br/>Voxtral HF Plugin]

No cross-module dependencies detected.

CLI Reference

No CLI commands found in this project.

Module Overview

Detailed documentation for each module in the project:

Voxtral HF Plugin (plugin.ipynb)

Plugin implementation for Mistral Voxtral transcription through Hugging Face Transformers

Import

from cjm_transcription_plugin_voxtral_hf.plugin import (
    VoxtralHFPlugin
)

Functions

@patch
def supports_streaming(
    self:VoxtralHFPlugin
) -> bool
    "Check if this plugin supports streaming transcription."
@patch
def execute_stream(
    self:VoxtralHFPlugin,
    audio: Union[AudioData, str, Path],  # Audio data or path to audio file
    **kwargs  # Additional plugin-specific parameters
) -> Generator[str, None, TranscriptionResult]:  # Yields text chunks, returns final result
    """
    Stream transcription results chunk by chunk.
    
    Args:
        audio: Audio data or path to audio file
        **kwargs: Additional plugin-specific parameters
        
    Yields:
        str: Partial transcription text chunks as they become available
        
    Returns:
        TranscriptionResult: Final complete transcription with metadata
    """

Classes

class VoxtralHFPlugin:
    def __init__(self):
        """Initialize the Voxtral HF plugin with default configuration."""
        self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
        self.config = {}
        self.model = None
        self.processor = None
        self.device = None
        self.dtype = None
    
    @property
    def name(
        self
    ) -> str:  # Returns the plugin name
    "Mistral Voxtral transcription plugin via Hugging Face Transformers."
    
    def __init__(self):
            """Initialize the Voxtral HF plugin with default configuration."""
            self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
            self.config = {}
            self.model = None
            self.processor = None
            self.device = None
            self.dtype = None
        
        @property
        def name(
            self
        ) -> str:  # Returns the plugin name
        "Initialize the Voxtral HF plugin with default configuration."
    
    def name(
            self
        ) -> str:  # Returns the plugin name
        "Get the plugin name identifier."
    
    def version(
            self
        ) -> str:  # Returns the plugin version
        "Get the plugin version string."
    
    def supported_formats(
            self
        ) -> List[str]:  # Returns list of supported audio formats
        "Get the list of supported audio file formats."
    
    def get_config_schema(
            self
        ) -> Dict[str, Any]:  # Returns the configuration schema dictionary
        "Return configuration schema for Voxtral HF."
    
    def get_current_config(
            self
        ) -> Dict[str, Any]:  # Returns the current configuration dictionary
        "Return current configuration."
    
    def initialize(
            self,
            config: Optional[Dict[str, Any]] = None  # Configuration dictionary to initialize the plugin
        ) -> None
        "Initialize the plugin with configuration."
    
    def execute(
            self,
            audio: Union[AudioData, str, Path],  # Audio data or path to audio file to transcribe
            **kwargs #  Additional arguments to override config
        ) -> TranscriptionResult:  # Returns transcription result with text and metadata
        "Transcribe audio using Voxtral."
    
    def is_available(
            self
        ) -> bool:  # Returns True if Voxtral and its dependencies are available
        "Check if Voxtral is available."
    
    def cleanup(
            self
        ) -> None
        "Clean up resources with aggressive memory management."

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cjm_transcription_plugin_voxtral_hf-0.0.3.tar.gz (14.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file cjm_transcription_plugin_voxtral_hf-0.0.3.tar.gz.

File metadata

File hashes

Hashes for cjm_transcription_plugin_voxtral_hf-0.0.3.tar.gz
Algorithm Hash digest
SHA256 38bba843323b7db8cf9b1536d1a94fad017aebbe715c6b332c0d872098fe91cc
MD5 35f5449db42d0efbef34673f17a1c7f6
BLAKE2b-256 9f2473ed6a69024214ec48e210835a7b7bfb4d80a7c44de6fab53aae68dc6dc2

See more details on using hashes here.

File details

Details for the file cjm_transcription_plugin_voxtral_hf-0.0.3-py3-none-any.whl.

File metadata

File hashes

Hashes for cjm_transcription_plugin_voxtral_hf-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 3d3eb039f25d1603f0c56414df62a3636580a3d53691f77e4bba0ad25f43105f
MD5 7010c40639ffb0549c62be3f8011e675
BLAKE2b-256 f77eb3c749b2edabc4b3188e8ccb1a076e0544f36b77d03d88ecbf520a33bbd0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page