POCKETSPHINX_PITCH(1)

💖 POCKETSPHINX_PITCH 💖

okay bestie, welcome to the manual page for pocketsphinx_pitch, from the General Commands Manual section of your local man situation (section 1, iykyk). this is a command-line tool and it is literally about finding the pitch in audio files. like, it listens to your audio and goes "hmm yes, this has a vibe, and the vibe is a frequency." obsessed. 🎀

---

✨ NAME ✨

spocketphinx_pitch — extract pitch from audio files

(yes the name up there has a lil extra s on the front, no I will not be fixing it, that's what the page says and we respect the page 💅)

---

🌸 SYNOPSIS 🌸

pocketsphinx_pitch [ options ]...

---

🦋 DESCRIPTION 🦋

so basically: this program reads audio files and analyzes them for pitch and voicing. that's the whole thing. it's giving "audio in, pitch knowledge out." ✨

---

👑 OPTIONS 👑

• -c — the file you want to use for batch processing.
• -di — a directory, and your input file names are relative to this one, if you define it.
• -do — a directory, and your output files are relative to this one.
• -ei — the extension to be applied to all input files.
• -eo — the extension to be applied to all output files.
• -flen — number of seconds in each analysis frame. heads up, this one needs to be greater than twice the longest period you wish to detect. so like, to detect down to 80Hz you need a frame length of 2.0/80 = 0.025. math is math, bestie. 🧮
• -fshift — frame shift: the number of seconds between each analysis frame.
• -i — the audio input file.
• -input_endian — endianness of audio data. (it will be determined automatically if you don't give it.)
• -mswav — defines the input format as Microsoft Wav (RIFF).
• -nist — defines the input format as NIST sphere.
• -nskip — if a control file was specified, the number of utterances to skip at the head of the file.
• -o — the text output file. (standard output will be used if you don't give one.)
• -raw — defines the input format as raw binary data.
• -runlen — if a control file was specified, the number of utterances to process. (see -nskip too, they're besties 👯)
• -samprate — sampling rate of audio data. (it will be determined automatically if 0.)
• -search_range — the fraction of the best local estimate to use as a search range for smoothing.
• -smooth_window — number of frames on either side of the current frame to use for smoothing.
• -voice_thresh — threshold of normalized difference under which to search for the fundamental period.

---

🫶 AUTHOR 🫶

David Huggins-Daines <dhdaines@gmail.com>

---

💜 COPYRIGHT 💜

Copyright © 2007-2008 Carnegie Mellon University. See the file COPYING included with this package for more information.

---

okay and that's the whole page, we ate and left no crumbs 🍓. this was page POCKETSPHINX_PITCH(1) from the General Commands Manual, dated 2007-05-12 — like, ancient in internet years but still iconic. go analyze some pitch, bestie, you got this 💖✨🌈