P/j^. ddlZddlmZmZmZddlZddlmZddlmZm Z ddl m Z m ZGddZdej fd ZGd d Zd ed edededeedee f dZdej fdZGddZy)N)IteratorListOptional)Tensor)_get_afilter_descStreamingMediaDecoder) CodecConfigStreamingMediaEncoderc(eZdZdZdZdefdZdZy)_StreamingIOBufferz6Streaming Bytes IO buffer. Data are dropped when read.cg|_yN)_buffer)selfs Z/root/repos/pocs/video-evals/.venv/lib/python3.12/site-packages/torchaudio/io/_effector.py__init__z_StreamingIOBuffer.__init__s $& bcR|r|jj|t|Sr)rappendlen)rrs rwritez_StreamingIOBuffer.writes LL   "1v rc|jsyt|jd|kr|jjdS|jdd|}|jd|d|jd<|S)zMPop the oldest byte string. It does not necessary return the requested amountrrN)rrpop)rnrets rrz_StreamingIOBuffer.popsk|| t||A 1 $<<##A& &ll1obq!,,q/!"- Q rN)__name__ __module__ __qualname____doc__rbytesrrrrr r s@'u rr dtypec tjdtjdtjdtjdtj di}||vrt d|d|j||S)Nu8s16s32fltdblUnsupported dtype is provided . Supported dtypes are: torchuint8int16int32float32float64 ValueErrorkeysr#typess r_get_sample_fmtr7!so T U U u u  E E9%@XY^YcYcYeXfghh <rcFeZdZdZdededededeedeedefd Z d Z y ) _AudioStreamingEncoderz3Given a waveform, encode on-demand and return bytessrc sample_rateeffectmuxerencoder codec_configframes_per_chunkc>||_t|_t|j||_|jj |j d|t|j||||jj||_ d|_ yN)format) num_channelsr;rCr> filter_descr?r) r:r buffer StreamWriterwriteradd_audio_streamsizer7r#openfpci_iter)rr:r;r<r=r>r?r@s rrz_AudioStreamingEncoder.__init__1s(* "4;;u=  $$!#"399-% %  #  rch|jjs|jdk\r|jj d|j |j|j|j z|xj|j z c_|j|j jdk\r;|jj|jjd|_|jjs|jdk\r|jj|S)Nr) rGrrNrIwrite_audio_chunkr:rMrKflushcloser)rrs rreadz_AudioStreamingEncoder.readNs++%%$++*: KK ) )!TXXdkkDKKRVRZRZDZ-[ \ KK488 #K{{dhhmmA.. !!# !!#  ++%%$++*:{{q!!rN) rrrr rintstrrr rrTr"rrr9r9.s\=     # {+:"rr9r:r;r<r=r>r?cJtj}t||}|j|j d|t |j ||||j5|jd|ddd|jd|S#1swYxYwrB) ioBytesIOrHrJrKr7r#rLrQseek)r:r;r<r=r>r?rGrIs r_encoder[YsZZ\F & /F XXa[syy)!  )  C() KKN M))s +BB"c tjdtjdtjdtjdtj di}||vrt d|d|j||S)Nr%s16les32lef32lef64ler*r+r,r5s r _get_muxerraqsq  T W W w w  E E9%@XY^YcYcYeXfghh <rc eZdZdZ ddddddeedeedeedeed ef d Zdd Z dd e d e dee de fdZ dd e d e de dee de e f dZy) AudioEffectoraApply various filters and/or codecs to waveforms. .. versionadded:: 2.1 Args: effect (str or None, optional): Filter expressions or ``None`` to apply no filter. See https://ffmpeg.org/ffmpeg-filters.html#Audio-Filters for the details of filter syntax. format (str or None, optional): When provided, encode the audio into the corresponding format. Default: ``None``. encoder (str or None, optional): When provided, override the encoder used by the ``format``. Default: ``None``. codec_config (CodecConfig or None, optional): When provided, configure the encoding codec. Should be provided in conjunction with ``format`` option. pad_end (bool, optional): When enabled, and if the waveform becomes shorter after applying effects/codec, then pad the end with silence. Example - Basic usage To use ``AudioEffector``, first instantiate it with a set of ``effect`` and ``format``. >>> # instantiate the effector >>> effector = AudioEffector(effect=..., format=...) Then, use :py:meth:`~AudioEffector.apply` or :py:meth:`~AudioEffector.stream` method to apply them. >>> # Apply the effect to the whole waveform >>> applied = effector.apply(waveform, sample_rate) >>> # Apply the effect chunk-by-chunk >>> for chunk in effector.stream(waveform, sample_rate): >>> ... Example - Applying effects Please refer to https://ffmpeg.org/ffmpeg-filters.html#Filtergraph-description for the overview of filter description, and https://ffmpeg.org/ffmpeg-filters.html#toc-Audio-Filters for the list of available filters. Tempo - https://ffmpeg.org/ffmpeg-filters.html#atempo >>> AudioEffector(effect="atempo=1.5") Echo - https://ffmpeg.org/ffmpeg-filters.html#aecho >>> AudioEffector(effect="aecho=0.8:0.88:60:0.4") Flanger - https://ffmpeg.org/ffmpeg-filters.html#flanger >>> AudioEffector(effect="aflanger") Vibrato - https://ffmpeg.org/ffmpeg-filters.html#vibrato >>> AudioEffector(effect="vibrato") Tremolo - https://ffmpeg.org/ffmpeg-filters.html#tremolo >>> AudioEffector(effect="vibrato") You can also apply multiple effects at once. >>> AudioEffector(effect="") Example - Applying codec One can apply codec using ``format`` argument. ``format`` can be audio format or container format. If the container format supports multiple encoders, you can specify it with ``encoder`` argument. Wav format (no compression is applied but samples are converted to 16-bit signed integer) >>> AudioEffector(format="wav") Ogg format with default encoder >>> AudioEffector(format="ogg") Ogg format with vorbis >>> AudioEffector(format="ogg", encoder="vorbis") Ogg format with opus >>> AudioEffector(format="ogg", encoder="opus") Webm format with opus >>> AudioEffector(format="webm", encoder="opus") Example - Applying codec with configuration Reference: https://trac.ffmpeg.org/wiki/Encode/MP3 MP3 with default config >>> AudioEffector(format="mp3") MP3 with variable bitrate >>> AudioEffector(format="mp3", codec_config=CodecConfig(qscale=5)) MP3 with constant bitrate >>> AudioEffector(format="mp3", codec_config=CodecConfig(bit_rate=32_000)) NT)r>r?pad_endr<rCr>r?rdcl||| td||_||_||_||_||_y)NzM`encoder` and/or `condec_config` opions are provided without `format` option.)r3r<rCr>r?rd)rr<rCr>r?rds rrzAudioEffector.__init__sD >"l&> !pqq   ( rc 0|j\}}|j1|j}|j}i} |jdk(r&||d} nt|j}d}||d} |%t |||j |||j} n%t|||j |||j|} ||n|} t| t|j|} |jr| d|} t| || } | j|xsdd| | S)Nmulaw)r;channelsz,apad=whole_len=)rCoptionrP)rF)shaperCr>rar#r[r<r?r9rr7rd StreamReaderrJ)rwaveformr;output_sample_rater@ num_framesrEr=r>rir: output_srrFreaders r _get_readerzAudioEffector._get_readers##+>> L ;; "KKEllGF{{g%,7=,Yx~~.EG(3}l^UF  #(KeWdN_N_`C(+t{{E7DDUDUWgC$6#=KCU ' ?8>>3RT`a <<(M)9*FKc%? 0 6B T rrlr;rmreturnc|jdk7rtd|j|jdk(r|S|j|||}|j |j \}t |S)aApply the effect and/or codecs to the whole tensor. Args: waveform (Tensor): The input waveform. Shape: ``(time, channel)`` sample_rate (int): Sample rate of the input waveform. output_sample_rate (int or None, optional): Output sample rate. If provided, override the output sample rate. Otherwise, the resulting tensor is resampled to have the same sample rate as the input. Default: ``None``. Returns: Tensor: Resulting Tensor. Shape: ``(time, channel)``. The number of frames could be different from that of the input. -Expected the input waveform to be 2D. Found: r)ndimr3numelrqprocess_all_packets pop_chunksr)rrlr;rmrpapplieds rapplyzAudioEffector.apply"sv" ==A LX]]O\] ] >> q O!!(K9KL""$&&( grr@c#K|jdk7rtd|j|jdk(r|S|j||||}|j D]\}t |yw)aZApply the effect and/or codecs to the given tensor chunk by chunk. Args: waveform (Tensor): The input waveform. Shape: ``(time, channel)`` sample_rate (int): Sample rate of the waveform. frames_per_chunk (int): The number of frames to return at a time. output_sample_rate (int or None, optional): Output sample rate. If provided, override the output sample rate. Otherwise, the resulting tensor is resampled to have the same sample rate as the input. Default: ``None``. Returns: Iterator[Tensor]: Series of processed chunks. Shape: ``(time, channel)``, where the the number of frames matches ``frames_per_chunk`` except the last chunk, which could be shorter. rtrurN)rvr3rwrqstreamr)rrlr;r@rmrprzs rr}zAudioEffector.stream>sx* ==A LX]]O\] ] >> q O!!(K9KM]^ --/ "JW/ ! "sA6A8)NNr)rrrr rrVr boolrrqrrUr{rr}r"rrrcrcsnd!% $ "&.2   #  {+ $@f3HUXMek:nr""-0"DG"]efi]j" & "rrc)rXtypingrrrr-r!torio.io._streaming_media_decoderrrrk!torio.io._streaming_media_encoderr r rHr r#r7r9rUrVr[rarcr"rrrs ++ f`, 5;; ("("V     c]  ;' 0 ekk \"\"r