U %d`@sLddlmZddlmZddlmZmZmZmZddl Z ddl Z eGdddZ eGddde Z eGd d d e Z dZd Zd Zd ZdZdZdZdZdZdZdZdZddZeGdddZddZddddd Zd!dddd"d#d$Zd%d&Zd'Z d(Z!d)Z"d*Z#d+Z$d,Z%d-Z&ee e!e"e$e%d.Z'ee e!e#e$e%e&d/Z(Gd0d1d1Z)dS)2) annotations) dataclass)DictIteratorOptionalTupleNc@sJeZdZUdZded<ded<ded<ded<ded <ded <ded <d S) StreamReaderSourceStreamakStreamReaderSourceStream() The metadata of a source stream. This class is used when representing streams of media type other than `audio` or `video`. When source stream is `audio` or `video` type, :py:class:`SourceAudioStream` and :py:class:`SourceVideoStream`, which reports additional media-specific attributes, are used respectively. str media_typecodeccodec_long_name Optional[str]format Optional[int]bit_rate num_framesbits_per_sampleN__name__ __module__ __qualname____doc____annotations__rr@/tmp/pip-unpacked-wheel-lbdmvq91/torchaudio/io/_stream_reader.pyr s   rc@s"eZdZUdZded<ded<dS)StreamReaderSourceAudioStreama StreamReaderSourceAudioStream() The metadata of an audio source stream. In addition to the attributes reported by :py:func:`StreamReaderSourceStream`, when the source stream is audio type, then the following additional attributes are reported. float sample_rateint num_channelsNrrrrrrBs  rc@s*eZdZUdZded<ded<ded<dS)StreamReaderSourceVideoStreama StreamReaderSourceVideoStream() The metadata of a video source stream. In addition to the attributes reported by :py:func:`StreamReaderSourceStream`, when the source stream is audio type, then the following additional attributes are reported. rwidthheightr frame_rateNrrrrrr Ss  r  c Cs|t}|t}|t}|t}|t}|t}|t}|dkrbt||||||||t|t d S|dkrt ||||||||t |t |t d St|||dddddS)Naudio) r r r rrrrrrvideo) r r r rrrrr!r"r#)r r r rrrr) _MEDIA_TYPE_CODEC _CODEC_LONG_FORMAT _BIT_RATE _NUM_FRAMES_BPSr _SAMPLE_RATE _NUM_CHANNELSr _WIDTH_HEIGHT _FRAME_RATEr)ir Z codec_namer fmtrrZbpsrrr _parse_sixsR  r?c@s"eZdZUdZded<ded<dS)StreamReaderOutputStreamzNOutputStream() Output stream configured on :py:class:`StreamReader`. rZ source_indexr Zfilter_descriptionNrrrrrr@s r@cCst|d|dS)Nrr$)r@r=rrr _parse_oisrBrr )rr>cCsFg}|dk r|d||dk r4|d||rBd|SdS)Nz aresample=zaformat=sample_fmts=,appendjoin)rr>descsrrr_get_afilter_descs rHOptional[float])r#r!r"r>cCsg}|dk r|d|g}|dk r8|d||dk rP|d||rj|dd||dk r|d||rd|SdS)Nzfps=zwidth=zheight=zscale=:zformat=pix_fmts=rCrD)r#r!r"r>rGZscalesrrr_get_vfilter_descsrKc sfdd}|S)Ncs|jjf|_|SN)rr)objkwargsrr decoratorsz_format_doc..decoratorr)rOrPrrNr _format_docs rQzNumber of frames returned as one chunk. If the source stream is exhausted before enough frames are buffered, then the chunk is returned as-is.zInternal buffer size. When the number of chunks buffered exceeds this number, old frames are dropped. Default: ``3``.zcThe source audio stream index. If omitted, :py:attr:`default_audio_stream` is used.zcThe source video stream index. If omitted, :py:attr:`default_video_stream` is used.zThe name of the decoder to be used. When provided, use the specified decoder instead of the default one. To list the available decoders, you can use `ffmpeg -decoders` command. Default: ``None``.zOptions passed to decoder. Mapping from str to str. To list decoder options for a decoder, you can use `ffmpeg -h decoder=` command. Default: ``None``.aEnable hardware acceleration. When video is decoded on CUDA hardware, for example `decode="h264_cuvid"`, passing CUDA device indicator to `hw_accel` (i.e. `hw_accel="cuda:0"`) will place the resulting frames directly on the specifiec CUDA device. If `None`, the frame will be moved to CPU memory. Default: ``None``.)frames_per_chunkbuffer_chunk_size stream_indexdecoderdecoder_option)rRrSrTrUrVhw_accelc @steZdZdZdDdddddd d Zed d Zed dZeddZeddZ dddddZ dddddZ ddddZ e dEddd dddd d!d"d#ZedFddd ddddd d d d% d&d'Ze dGddd dddd(d)d*ZedHddd ddddd+d,d-Zdd.d/d0ZdId2ddd3d4d5Zd6d7Zd8d9d:d;ZdZd2ddd3d?d@ZdJd2ddAd3dBdCZdS)K StreamReadera Fetch and decode audio/video streams chunk by chunk. For the detailed usage of this class, please refer to the tutorial. Args: src (str or file-like object): The media source. If string-type, it must be a resource indicator that FFmpeg can handle. This includes a file path, URL, device identifier or filter expression. The supported value depends on the FFmpeg found in the system. If file-like object, it must support `read` method with the signature `read(size: int) -> bytes`. Additionally, if the file-like object has `seek` method, it uses the method when parsing media metadata. This improves the reliability of codec detection. The signagure of `seek` method must be `seek(offset: int, whence: int) -> int`. Please refer to the following for the expected signature and behavior of `read` and `seek` method. - https://docs.python.org/3/library/io.html#io.BufferedIOBase.read - https://docs.python.org/3/library/io.html#io.IOBase.seek format (str or None, optional): Override the input format, or specify the source sound device. Default: ``None`` (no override nor device input). This argument serves two different usecases. 1) Override the source format. This is useful when the input data do not contain a header. 2) Specify the input source device. This allows to load media stream from hardware devices, such as microphone, camera and screen, or a virtual device. .. note:: This option roughly corresponds to ``-f`` option of ``ffmpeg`` command. Please refer to the ffmpeg documentations for the possible values. https://ffmpeg.org/ffmpeg-formats.html For device access, the available values vary based on hardware (AV device) and software configuration (ffmpeg build). https://ffmpeg.org/ffmpeg-devices.html option (dict of str to str, optional): Custom option passed when initializing format context (opening source). You can use this argument to change the input source before it is passed to decoder. Default: ``None``. buffer_size (int): The internal buffer size in byte. Used only when `src` is file-like object. Default: `4096`. Nr r zOptional[Dict[str, str]]r)srcroption buffer_sizecCst|tr tjj||||_n(t|dr@tj |||||_nt d|j }|dkr^dn||_ |j }|dkrzdn||_dS)Nreadz0`src` must be either string or file-like object.r) isinstancer torchclasses torchaudioZffmpeg_StreamReader_behasattrZ_torchaudio_ffmpegZStreamReaderFileObj ValueErrorZfind_best_audio_stream_default_audio_streamZfind_best_video_stream_default_video_stream)selfrZrr[r\r=rrr__init__Us    zStreamReader.__init__cCs |jS)zRNumber of streams found in the provided media source. :type: int )rbnum_src_streamsrgrrrrihszStreamReader.num_src_streamscCs |jS)zPNumber of output streams configured by client code. :type: int )rbnum_out_streamsrjrrrrkpszStreamReader.num_out_streamscCs|jS)znThe index of default audio stream. ``None`` if there is no audio stream :type: Optional[int] )rerjrrrdefault_audio_streamxsz!StreamReader.default_audio_streamcCs|jS)znThe index of default video stream. ``None`` if there is no video stream :type: Optional[int] )rfrjrrrdefault_video_streamsz!StreamReader.default_video_streamz&torchaudio.io.StreamReaderSourceStream)r=returncCst|j|S)zGet the metadata of source stream Args: i (int): Stream index. Returns: SourceStream )r?rbget_src_stream_inforgr=rrrrosz StreamReader.get_src_stream_infoz&torchaudio.io.StreamReaderOutputStreamcCst|j|S)zGet the metadata of output stream Args: i (int): Stream index. Returns: OutputStream )rBrbget_out_stream_inforprrrrqsz StreamReader.get_out_stream_infor) timestampcCs|j|dS)z}Seek the stream to the given timestamp [second] Args: timestamp (float): Target time in second. N)rbseek)rgrrrrrrsszStreamReader.seekr&fltpr)rRrSrTrUrVrrc Cs||||||t||dS)aAdd output audio stream Args: frames_per_chunk (int): {frames_per_chunk} buffer_chunk_size (int, optional): {buffer_chunk_size} stream_index (int or None, optional): {stream_index} decoder (str or None, optional): {decoder} decoder_option (dict or None, optional): {decoder_option} format (str, optional): Output sample format (precision). If ``None``, the output chunk has dtype corresponding to the precision of the source audio. Otherwise, the sample is converted and the output dtype is changed as following. - ``"u8p"``: The output is ``torch.uint8`` type. - ``"s16p"``: The output is ``torch.int16`` type. - ``"s32p"``: The output is ``torch.int32`` type. - ``"s64p"``: The output is ``torch.int64`` type. - ``"fltp"``: The output is ``torch.float32`` type. - ``"dblp"``: The output is ``torch.float64`` type. Default: ``"fltp"``. sample_rate (int or None, optional): If provided, resample the audio. N)add_audio_streamrH)rgrRrSrTrUrVrrrrradd_basic_audio_streams+z#StreamReader.add_basic_audio_streamrgb24) rRrSrTrUrVrWrr#r!r"c Cs$|||||||t|| | |dS)a'Add output video stream Args: frames_per_chunk (int): {frames_per_chunk} buffer_chunk_size (int, optional): {buffer_chunk_size} stream_index (int or None, optional): {stream_index} decoder (str or None, optional): {decoder} decoder_option (dict or None, optional): {decoder_option} hw_accel (str or None, optional): {hw_accel} format (str, optional): Change the format of image channels. Valid values are, - ``"rgb24"``: 8 bits * 3 channels (R, G, B) - ``"bgr24"``: 8 bits * 3 channels (B, G, R) - ``"yuv420p"``: 8 bits * 3 channels (Y, U, V) - ``"gray"``: 8 bits * 1 channels Default: ``"rgb24"``. frame_rate (int or None, optional): If provided, change the frame rate. width (int or None, optional): If provided, change the image width. Unit: Pixel. height (int or None, optional): If provided, change the image height. Unit: Pixel. N)add_video_streamrK) rgrRrSrTrUrVrWrr#r!r"rrradd_basic_video_streams, z#StreamReader.add_basic_video_stream)rRrSrTrUrV filter_desccCs@|dkr|jn|}|dkr"td|j||||||p8idS)adAdd output audio stream Args: frames_per_chunk (int): {frames_per_chunk} buffer_chunk_size (int, optional): {buffer_chunk_size} stream_index (int or None, optional): {stream_index} decoder (str or None, optional): {decoder} decoder_option (dict or None, optional): {decoder_option} filter_desc (str or None, optional): Filter description. The list of available filters can be found at https://ffmpeg.org/ffmpeg-filters.html Note that complex filters are not supported. NzThere is no audio stream.)rl RuntimeErrorrbru)rgrRrSrTrUrVrzr=rrrruszStreamReader.add_audio_stream)rRrSrTrUrVrWrzc CsB|dkr|jn|}|dkr"td|j||||||p8i|dS)aAdd output video stream Args: frames_per_chunk (int): {frames_per_chunk} buffer_chunk_size (int, optional): {buffer_chunk_size} stream_index (int or None, optional): {stream_index} decoder (str or None, optional): {decoder} decoder_option (dict or None, optional): {decoder_option} hw_accel (str or None, optional): {hw_accel} filter_desc (str or None, optional): Filter description. The list of available filters can be found at https://ffmpeg.org/ffmpeg-filters.html Note that complex filters are not supported. NzThere is no video stream.)rmr{rbrx) rgrRrSrTrUrVrWrzr=rrrrx7szStreamReader.add_video_streamrAcCs|j|dS)zoRemove an output stream. Args: i (int): Index of the output stream to be removed. N)rb remove_streamrprrrr|cszStreamReader.remove_stream$@rI)timeoutbackoffrncCs|j||S)aRead the source media and process one packet. If a packet is read successfully, then the data in the packet will be decoded and passed to corresponding output stream processors. If the packet belongs to a source stream that is not connected to an output stream, then the data are discarded. When the source reaches EOF, then it triggers all the output stream processors to enter drain mode. All the output stream processors flush the pending frames. Args: timeout (float or None, optional): Timeout in milli seconds. This argument changes the retry behavior when it failed to process a packet due to the underlying media resource being temporarily unavailable. When using a media device such as a microphone, there are cases where the underlying buffer is not ready. Calling this function in such case would cause the system to report `EAGAIN (resource temporarily unavailable)`. * ``>=0``: Keep retrying until the given time passes. * ``0<``: Keep retrying forever. * ``None`` : No retrying and raise an exception immediately. Default: ``None``. Note: The retry behavior is applicable only when the reason is the unavailable resource. It is not invoked if the reason of failure is other. backoff (float, optional): Time to wait before retrying in milli seconds. This option is effective only when `timeout` is effective. (not ``None``) When `timeout` is effective, this `backoff` controls how long the function should wait before retrying. Default: ``10.0``. Returns: int: ``0`` A packet was processed properly. The caller can keep calling this function to buffer more frames. ``1`` The streamer reached EOF. All the output stream processors flushed the pending frames. The caller should stop calling this method. )rbprocess_packet)rgr~rrrrrks9zStreamReader.process_packetcCs|jdS)z%Process packets until it reaches EOF.N)rbprocess_all_packetsrjrrrrsz StreamReader.process_all_packetsbool)rncCs |jS)zFReturns true if all the output streams have at least one chunk filled.)rbis_buffer_readyrjrrrrszStreamReader.is_buffer_readyzTuple[Optional[torch.Tensor]]cCs |jS)zPop one chunk from all the output stream buffers. Returns: Tuple[Optional[Tensor]]: Buffer contents. If a buffer does not contain any frame, then `None` is returned instead. )rb pop_chunksrjrrrrszStreamReader.pop_chunkscCs&|s"|||}|dkr|SqdS)aKeep processing packets until all buffers have at least one chunk Returns: int: ``0`` Packets are processed properly and buffers are ready to be popped once. ``1`` The streamer reached EOF. All the output stream processors flushed the pending frames. The caller should stop calling this method. r)rr)rgr~rcoderrr _fill_buffers  zStreamReader._fill_bufferz,Iterator[Tuple[Optional[torch.Tensor], ...]]ccsV|jdkrtd|||r q,|Vq|}tdd|DrJdS|Vq,dS)aReturn an iterator that generates output tensors Arguments: timeout (float or None, optional): See :py:func:`~StreamReader.process_packet`. (Default: ``None``) backoff (float, optional): See :py:func:`~StreamReader.process_packet`. (Default: ``10.0``) Returns: Iterator[Tuple[Optional[torch.Tensor], ...]]: Iterator that yields a tuple of chunks that correspond to the output streams defined by client code. If an output stream is exhausted, then the chunk Tensor is substituted with ``None``. The iterator stops if all the output streams are exhausted. rzNo output stream is configured.css|]}|dkVqdSrLr).0crrr sz&StreamReader.stream..N)rkr{rrall)rgr~rchunksrrrstreams   zStreamReader.stream)NNrY)r&NNNrtN) r&NNNNrwNNN)r&NNNN)r&NNNNN)Nr})Nr})rrrrrhpropertyrirkrlrmrorqrs_format_audio_argsrv_format_video_argsryrurxr|rrrrrrrrrrrXsvB      3$5(+; rX)* __future__rZ dataclassesrtypingrrrrr_rarrr r1r2r3r4r5r6r7r8r9r:r;r<r?r@rBrHrKrQZ_frames_per_chunkZ_buffer_chunk_sizeZ_audio_stream_indexZ_video_stream_index_decoderZ_decoder_optionZ _hw_accelrrrXrrrrsh  7,