DrDavis's picture
Upload folder using huggingface_hub
17c6d62 verified

FeatureExtractors๋ฅผ ์œ„ํ•œ ์œ ํ‹ธ๋ฆฌํ‹ฐ [[utilities-for-featureextractors]]

์ด ํŽ˜์ด์ง€๋Š” ์˜ค๋””์˜ค [FeatureExtractor]๊ฐ€ ๋‹จ์‹œ๊ฐ„ ํ‘ธ๋ฆฌ์— ๋ณ€ํ™˜(Short Time Fourier Transform) ๋˜๋Š” *๋กœ๊ทธ ๋ฉœ ์ŠคํŽ™ํŠธ๋กœ๊ทธ๋žจ(log mel spectrogram)*๊ณผ ๊ฐ™์€ ์ผ๋ฐ˜์ ์ธ ์•Œ๊ณ ๋ฆฌ์ฆ˜์„ ์‚ฌ์šฉํ•˜์—ฌ ์›์‹œ ์˜ค๋””์˜ค์—์„œ ํŠน์ˆ˜ํ•œ ํŠน์„ฑ์„ ๊ณ„์‚ฐํ•˜๋Š” ๋ฐ ์‚ฌ์šฉํ•  ์ˆ˜ ์žˆ๋Š” ์œ ํ‹ธ๋ฆฌํ‹ฐ ํ•จ์ˆ˜๋“ค์„ ๋‚˜์—ดํ•ฉ๋‹ˆ๋‹ค.

์ด ํ•จ์ˆ˜๋“ค ๋Œ€๋ถ€๋ถ„์€ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ ๋‚ด ์˜ค๋””์˜ค ์ฒ˜๋ฆฌ ์ฝ”๋“œ๋ฅผ ์—ฐ๊ตฌํ•  ๋•Œ์—๋งŒ ์œ ์šฉํ•ฉ๋‹ˆ๋‹ค.

์˜ค๋””์˜ค ๋ณ€ํ™˜ [[transformers.audio_utils.hertz_to_mel]]

[[autodoc]] audio_utils.hertz_to_mel

[[autodoc]] audio_utils.mel_to_hertz

[[autodoc]] audio_utils.mel_filter_bank

[[autodoc]] audio_utils.optimal_fft_length

[[autodoc]] audio_utils.window_function

[[autodoc]] audio_utils.spectrogram

[[autodoc]] audio_utils.power_to_db

[[autodoc]] audio_utils.amplitude_to_db