o i @sDdZddlmZddlZddlmZddlmZGdddeZdS)z(Sliding Window for raw audio input data.)TupleN)check_argument_types) AbsFrontendc sreZdZdZ     ddededed effd d Zd ejd ejdeejejffddZ defddZ Z S) SlidingWindowaSliding Window. Provides a sliding window over a batched continuous raw audio tensor. Optionally, provides padding (Currently not implemented). Combine this module with a pre-encoder compatible with raw audio data, for example Sinc convolutions. Known issues: Output length is calculated incorrectly if audio shorter than win_length. WARNING: trailing values are discarded - padding not implemented yet. There is currently no additional window function applied to input values. N win_length hop_lengthchannelspaddingcs6tsJt||_||_||_||_||_dS)aLInitialize. Args: win_length: Length of frame. hop_length: Relative starting point of next frame. channels: Number of input channels. padding: Padding (placeholder, currently not implemented). fs: Sampling rate (placeholder for compatibility, not used). N)rsuper__init__fsr r r r )selfr r r r r __class__R/home/ubuntu/.local/lib/python3.10/site-packages/espnet2/asr/frontend/windowing.pyrs   zSlidingWindow.__init__input input_lengthsreturnc Cs||}|d}|d}|j}|j}||||ddd}|d||j} | dddd} ||j|jd} | | fS)aBApply a sliding window on the input. Args: input: Input (B, T, C*D) or (B, T*C*D), with D=C=1. input_lengths: Input lengths within batch. Returns: Tensor: Output with dimensions (B, T, C, D), with D=win_length. Tensor: Output lengths within batch. rr)sizer r viewpermuteunfoldr contiguous) rrr input_sizeBTCD continuouswindowedoutputoutput_lengthsrrrforward6s zSlidingWindow.forwardcCs|jS)zDReturn output length of feature dimension D, i.e. the window length.)r )rrrr output_sizeQszSlidingWindow.output_size)rrrNN) __name__ __module__ __qualname____doc__intrtorchTensorrr(r) __classcell__rrrrrs0 r) r-typingrr/ typeguardr!espnet2.asr.frontend.abs_frontendrrrrrrs