:j> ddlZddlZddlmZddlmZmZddlZddl Z ddl m cm Z ddlmZdZdZdZdZeezZeeeZed zZeeeZeeeZefd ed ed ej6fd ZefdddedefdZedded e j<fdZ ddeeej6e j<fdededeeee j@ffdZ!y)N) lru_cache)OptionalUnion) exact_divi>ifilesrreturnc ddddd|dddd d d d t|d g}tj|ddj}tj|tjjjtjdz S#tj$r,}t d|j j|d}~wwxYw)a? Open an audio file and read as mono waveform, resampling as necessary Parameters ---------- file: str The audio file to open sr: int The sample rate to resample the audio if necessary Returns ------- A NumPy array containing the audio waveform, in float32 dtype. ffmpegz-nostdinz-threads0z-iz-fs16lez-ac1z-acodec pcm_s16lez-ar-T)capture_outputcheckzFailed to load audio: Ng@)str subprocessrunstdoutCalledProcessError RuntimeErrorstderrdecodenp frombufferint16flattenastypefloat32)r r cmdoutes c/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/whisperx/audio.py load_audior(s P              G  "nnSTBII ==bhh ' / / 1 8 8 Dw NN  ( (P3AHHOO4E3FGHaOPsDsC u ;;t v %&& VELL I'E ;;t v % EJJ.J !6EKK,=#=>Jt EE%:dd3C!U%u!U#!U#!UVE L ;;t v %JJuV}4J@E ;;t v % EJJ.J !6EKK,=#=>Jt FF5*-E L"Vs.E )maxsizen_melscH|dvs Jd|tjtjj tjj t dd5}tj|d|j|cdddS#1swYyxYw)a load the mel filterbank matrix for projecting STFT into a Mel spectrogram. Allows decoupling librosa dependency; saved using: np.savez_compressed( "mel_filters.npz", mel_80=librosa.filters.mel(sr=16000, n_fft=400, n_mels=80), ) )PzUnsupported n_mels: assetszmel_filters.npzmel_N) rloadospathjoindirname__file__r1 from_numpyto)r-r@fs r' mel_filtersrO^s Y ?"6vh ??    RWW__X.:KL ? D/ 2366v>???s $*BB!audiopaddingr-ctj|s0t|tr t |}tj |}||j |}|dkDrtj|d|f}tjtj |j}tj|tt|d}|dddfjdz}t|j|}||z}tj |d j#} tj$| | j'd z } | d zd z } | S) ap Compute the log-Mel spectrogram of Parameters ---------- audio: Union[str, np.ndarray, torch.Tensor], shape = (*) The path to audio or either a NumPy array or Tensor containing the audio waveform in 16 kHz n_mels: int The number of Mel-frequency filters, only 80 is supported padding: int Number of zero samples to pad to the right device: Optional[Union[str, torch.device]] If given, the audio tensor is moved to this device before STFT Returns ------- torch.Tensor, shape = (80, n_frames) A Tensor that contains the Mel spectrogram NrT)windowreturn_complex.r)r g|=)ming @g@)r1r2 isinstancerr(rLrMr7r8 hann_windowN_FFTr-stft HOP_LENGTHabsrOclamplog10maximummax) rPr@rQr-rSrY magnitudesfiltersmel_speclog_specs r'log_mel_spectrogramrdps8 ??5 ! eS !u%E  '  {ea\*   u % ( ( 6F ::eUJvd SDc3B3h##%*J%,,/G#H{{8/557H}}Xx||~';TensorrOr-rdrer'rxs; " $     ; & Y + 1nk:6k+>?%0(OS(Oc(OBJJ(OV&/rs4 4?? ??(15 / bjj%,,. // // U3 ,- . /re