OpenAI Whisper plugin for the cjm-transcription-plugin-system library - provides local speech-to-text transcription with configurable model selection and parameter control.
Project description
cjm-transcription-plugin-whisper
Install
pip install cjm_transcription_plugin_whisper
Project Structure
nbs/
├── meta.ipynb # Metadata introspection for the Whisper plugin used by cjm-ctl to generate the registration manifest.
└── plugin.ipynb # Plugin implementation for OpenAI Whisper transcription
Total: 2 notebooks across 1 directory
Module Dependencies
graph LR
meta[meta<br/>Metadata]
plugin[plugin<br/>Whisper Plugin]
plugin --> meta
1 cross-module dependencies detected
CLI Reference
No CLI commands found in this project.
Module Overview
Detailed documentation for each module in the project:
Metadata (meta.ipynb)
Metadata introspection for the Whisper plugin used by cjm-ctl to generate the registration manifest.
Import
from cjm_transcription_plugin_whisper.meta import (
get_plugin_metadata
)
Functions
def get_plugin_metadata() -> Dict[str, Any]: # Plugin metadata for manifest generation
"""Return metadata required to register this plugin with the PluginManager."""
# Calculate default DB path relative to the environment
# e.g., /opt/conda/envs/cjm-whisper/data/history.db
base_path = os.path.dirname(os.path.dirname(sys.executable))
data_dir = os.path.join(base_path, "data")
db_path = os.path.join(data_dir, "transcriptions.db")
# Ensure data directory exists
os.makedirs(data_dir, exist_ok=True)
return {
"name": "cjm-transcription-plugin-whisper",
"Return metadata required to register this plugin with the PluginManager."
Whisper Plugin (plugin.ipynb)
Plugin implementation for OpenAI Whisper transcription
Import
from cjm_transcription_plugin_whisper.plugin import (
WhisperPluginConfig,
WhisperLocalPlugin
)
Classes
@dataclass
class WhisperPluginConfig:
"Configuration for Whisper transcription plugin."
model: str = field(...)
device: str = field(...)
language: Optional[str] = field(...)
task: str = field(...)
temperature: float = field(...)
temperature_increment_on_fallback: Optional[float] = field(...)
beam_size: int = field(...)
best_of: int = field(...)
patience: float = field(...)
length_penalty: Optional[float] = field(...)
suppress_tokens: str = field(...)
initial_prompt: Optional[str] = field(...)
condition_on_previous_text: bool = field(...)
fp16: bool = field(...)
compression_ratio_threshold: float = field(...)
logprob_threshold: float = field(...)
no_speech_threshold: float = field(...)
word_timestamps: bool = field(...)
prepend_punctuations: str = field(...)
append_punctuations: str = field(...)
threads: int = field(...)
model_dir: Optional[str] = field(...)
compile_model: bool = field(...)
class WhisperLocalPlugin:
def __init__(self):
"""Initialize the Whisper plugin with default configuration."""
self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
self.config: WhisperPluginConfig = None
"OpenAI Whisper transcription plugin."
def __init__(self):
"""Initialize the Whisper plugin with default configuration."""
self.logger = logging.getLogger(f"{__name__}.{type(self).__name__}")
self.config: WhisperPluginConfig = None
"Initialize the Whisper plugin with default configuration."
def name(self) -> str: # Plugin name identifier
"""Get the plugin name identifier."""
return "whisper_local"
@property
def version(self) -> str: # Plugin version string
"Get the plugin name identifier."
def version(self) -> str: # Plugin version string
"""Get the plugin version string."""
return "1.0.0"
@property
def supported_formats(self) -> List[str]: # List of supported audio file formats
"Get the plugin version string."
def supported_formats(self) -> List[str]: # List of supported audio file formats
"""Get the list of supported audio file formats."""
return ["wav", "mp3", "flac", "m4a", "ogg", "webm", "mp4", "avi", "mov"]
def get_current_config(self) -> Dict[str, Any]: # Current configuration as dictionary
"Get the list of supported audio file formats."
def get_current_config(self) -> Dict[str, Any]: # Current configuration as dictionary
"""Return current configuration state."""
if not self.config
"Return current configuration state."
def get_config_schema(self) -> Dict[str, Any]: # JSON Schema for configuration
"""Return JSON Schema for UI generation."""
return dataclass_to_jsonschema(WhisperPluginConfig)
@staticmethod
def get_config_dataclass() -> WhisperPluginConfig: # Configuration dataclass
"Return JSON Schema for UI generation."
def get_config_dataclass() -> WhisperPluginConfig: # Configuration dataclass
"""Return dataclass describing the plugin's configuration options."""
return WhisperPluginConfig
def initialize(
self,
config: Optional[Any] = None # Configuration dataclass, dict, or None
) -> None
"Return dataclass describing the plugin's configuration options."
def initialize(
self,
config: Optional[Any] = None # Configuration dataclass, dict, or None
) -> None
"Initialize or re-configure the plugin (idempotent)."
def execute(
self,
audio: Union[AudioData, str, Path], # Audio data or path to audio file to transcribe
**kwargs # Additional arguments to override config
) -> TranscriptionResult: # Transcription result with text and metadata
"Transcribe audio using Whisper."
def is_available(self) -> bool: # True if Whisper and its dependencies are available
"""Check if Whisper is available."""
return WHISPER_AVAILABLE
def cleanup(self) -> None
"Check if Whisper is available."
def cleanup(self) -> None:
"""Clean up resources."""
if self.model is not None
"Clean up resources."
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file cjm_transcription_plugin_whisper-0.0.10.tar.gz.
File metadata
- Download URL: cjm_transcription_plugin_whisper-0.0.10.tar.gz
- Upload date:
- Size: 16.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
74a188f5ec2640e84b065c4c7896d842f6cb9fefda3d18a00279e5ff66afe6b5
|
|
| MD5 |
f20d7d9985a1ac6ee2097919f9717a2b
|
|
| BLAKE2b-256 |
d196582b3f6e52092afc414caeb2133c8cc06e2f1d266bed99011fec148a01f0
|
File details
Details for the file cjm_transcription_plugin_whisper-0.0.10-py3-none-any.whl.
File metadata
- Download URL: cjm_transcription_plugin_whisper-0.0.10-py3-none-any.whl
- Upload date:
- Size: 15.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.11.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5d999bb8c2bd01aabf458eac15d47697bc52cfbc7768797e751fffc1b71242e6
|
|
| MD5 |
af42236512067fceac87b021ec07750a
|
|
| BLAKE2b-256 |
848a4c3c6c7b12f6d9b0a4926b1aa9352f3fb8c03637bd97ac6314db4672d82a
|