scruffynerf/lyric_analysis

---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: album_name
dtype: string
- name: artist_name
dtype: string
- name: track_name
dtype: string
- name: acousticness
dtype: float64
- name: danceability
dtype: float64
- name: energy
dtype: float64
- name: instrumentalness
dtype: float64
- name: musical_key
dtype: string
- name: mode
dtype: string
- name: liveness
dtype: float64
- name: speechiness
dtype: float64
- name: audio_tempo
dtype: float64
- name: audio_time_signature
dtype: int64
- name: valence
dtype: float64
- name: loudness
dtype: float64
- name: popularity
dtype: int64
- name: lrclib_track_id
dtype: int64
- name: lrclib_lyrics_id
dtype: int64
- name: primary_genre
dtype: string
- name: genre_list
dtype: string
- name: genre_count
dtype: int64
- name: line_count
dtype: int64
- name: section_count
dtype: int64
- name: word_count
dtype: int64
- name: unique_word_count
dtype: int64
- name: syllable_count
dtype: int64
- name: avg_words_per_line
dtype: float64
- name: avg_syllables_per_line
dtype: float64
- name: avg_lines_per_section
dtype: float64
- name: duration_sec
dtype: int64
- name: lyric_tempo
dtype: float64
- name: lyric_time_signature
dtype: int64
- name: estimated_measures
dtype: float64
- name: words_per_measure
dtype: float64
- name: syllables_per_measure
dtype: float64
- name: unique_word_ratio
dtype: float64
- name: repetition_ratio
dtype: float64
- name: first_section_density
dtype: float64
- name: last_section_density
dtype: float64
- name: section_length_variance
dtype: float64
- name: syllable_stddev
dtype: float64
- name: mean_syllables_per_word
dtype: float64
- name: cadence_diversity_ratio
dtype: float64
- name: cadence_entropy
dtype: float64
- name: cadence_shift_rate
dtype: float64
splits:
- name: train
num_bytes: 1824306275
num_examples: 4388931
download_size: 563117965
dataset_size: 1824306275
---