U DAf @sddlZddlmZddlmZmZmZmZmZm Z m Z ddl m Z m Z mZmZmZddlmZddlmZddlmZedZddlZW5QRXeeZed Ze Gd d d ZdS) N)Path)AnyDictListLiteralOptionalUnionget_args)Document componentdefault_from_dictdefault_to_dictlogging) ByteStream) LazyImport)ComponentDevicez@Run 'pip install "openai-whisper>=20231106"' to install whisper.) basezbase.enlargezlarge-v1zlarge-v2zlarge-v3Zmediumz medium.ensmallzsmall.enZtinyztiny.enc@seZdZdZdeeeeeee fdddZ dddd Z eee fdd d Z e eee fdd d dZejeeddeeeeefeeee fdddZeeeeefeedddZeeeeefeee fdddZdS)LocalWhisperTranscriberaM Transcribes audio files using OpenAI's Whisper model in your local machine. For the supported audio formats, languages, and other parameters, see the [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper [github repository](https://github.com/openai/whisper). Usage example: ```python from haystack.components.audio import LocalWhisperTranscriber whisper = LocalWhisperTranscriber(model="small") whisper.warm_up() transcription = whisper.run(audio_files=["path/to/audio/file"]) ``` rNmodeldevicewhisper_paramscCsZt|ttkr4td|ddttd||_|p@i|_t ||_ d|_ dS)a Creates an instance of the LocalWhisperTranscriber component. :param model: Name of the model to use. Set it to one of the following values: :type model: Literal["tiny", "small", "medium", "large", "large-v2"] :param device: The device on which the model is loaded. If `None`, the default device is automatically selected. z Model name 'z$' not recognized. Choose one among: z, .N) whisper_importcheckr WhisperLocalModel ValueErrorjoinrrrZresolve_devicer_model)selfrrrr"K/tmp/pip-unpacked-wheel-z752163x/haystack/components/audio/whisper_local.py__init__6s   z LocalWhisperTranscriber.__init__)returncCs"|jstj|j|jd|_dS)z, Loads the model in memory. )rN)r whisperZ load_modelrrZto_torchr!r"r"r#warm_upPszLocalWhisperTranscriber.warm_upcCst||j|j|jdS)z{ Serializes the component to a dictionary. :returns: Dictionary with serialized data. r)r rrto_dictrr'r"r"r#r)WszLocalWhisperTranscriber.to_dict)datar%cCs2|d}|ddk r(t|d|d<t||S)z Deserializes the component from a dictionary. :param data: The dictionary to deserialize from. :returns: The deserialized component. Zinit_parametersrN)getr from_dictr )clsr*Z init_paramsr"r"r#r,`s z!LocalWhisperTranscriber.from_dict) documents)sourcesrcCs6|jdkrtd|dkr |j}|j|f|}d|iS)a6 Transcribes the audio files into a list of Documents, one for each input file. For the supported audio formats, languages, and other parameters, see the [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper [github repo](https://github.com/openai/whisper). :param audio_files: A list of paths or binary streams to transcribe. :returns: A dictionary with the following keys: - `documents`: A list of Documents, one for each file. The content of the document is the transcription text, while the document's metadata contains the values returned by the Whisper model, such as the alignment data and the path to the audio file used for the transcription. Nz`The component LocalWhisperTranscriber was not warmed up. Run 'warm_up()' before calling 'run()'.r.)r RuntimeErrorr transcribe)r!r/rr.r"r"r#runos zLocalWhisperTranscriber.run)r/r%c KsP|j|f|}g}|D]0\}}|d}t|d|i|d}||q|S)a Transcribes the audio files into a list of Documents, one for each input file. For the supported audio formats, languages, and other parameters, see the [Whisper API documentation](https://platform.openai.com/docs/guides/speech-to-text) and the official Whisper [github repo](https://github.com/openai/whisper). :param audio_files: A list of paths or binary streams to transcribe. :returns: A list of Documents, one for each file. textZ audio_file)contentmeta)_raw_transcribeitemspopr append) r!r/kwargstranscriptionsr.pathZ transcriptr4docr"r"r#r1s   z"LocalWhisperTranscriber.transcribec Ks|jdkrtd|dd}i}|D]}t|tsr;sourcer<fpZ transcriptionr"r"r#r6s     z'LocalWhisperTranscriber._raw_transcribe)rNN)N)__name__ __module__ __qualname____doc__rrrrrFrr$r(r) classmethodr,r Z output_typesrr rrrr2r1r6r"r"r"r#r#s"  ."r)rCpathlibrtypingrrrrrrr Zhaystackr r r r rZhaystack.dataclassesrZhaystack.lazy_importsrZhaystack.utilsrrr& getLoggerrIloggerrrr"r"r"r#s $