Audio Classification
Transformers
English
audio
audio-captioning
audio-tagging
audioset
whisper
speech-captioning
music-captioning
sound-effect-captioning
laion
ast
audio-spectrogram-transformer
Instructions to use laion/whisper-captioning-ensemble with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use laion/whisper-captioning-ensemble with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="laion/whisper-captioning-ensemble")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("laion/whisper-captioning-ensemble", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- .gitattributes +6 -0
- samples/freesound/audio_203313_391226.json +23 -0
- samples/freesound/audio_203313_391226.mp3 +3 -0
- samples/freesound/audio_206738_390405.json +23 -0
- samples/freesound/audio_206738_390405.mp3 +3 -0
- samples/freesound/audio_206747_390848.json +23 -0
- samples/freesound/audio_206747_390848.mp3 +0 -0
- samples/freesound/audio_238707_393020.json +23 -0
- samples/freesound/audio_238707_393020.mp3 +0 -0
- samples/freesound/audio_312332_389459.json +23 -0
- samples/freesound/audio_312332_389459.mp3 +3 -0
- samples/freesound/audio_315277_393270.json +23 -0
- samples/freesound/audio_315277_393270.mp3 +0 -0
- samples/freesound/audio_360573_395201.json +23 -0
- samples/freesound/audio_360573_395201.mp3 +3 -0
- samples/freesound/audio_389654_399191.json +23 -0
- samples/freesound/audio_389654_399191.mp3 +3 -0
- samples/freesound/audio_391770_402152.json +23 -0
- samples/freesound/audio_391770_402152.mp3 +0 -0
- samples/freesound/audio_41515_397745.json +23 -0
- samples/freesound/audio_41515_397745.mp3 +3 -0
- samples/freesound/upstream_captions.json +62 -0
.gitattributes
CHANGED
|
@@ -50,3 +50,9 @@ samples/music/music__suno_audio_129101_5_1823360.mp3 filter=lfs diff=lfs merge=l
|
|
| 50 |
samples/music/music__suno_audio_196211_4_1844520.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 51 |
samples/music/music__suno_audio_298525_3_1855480.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 52 |
samples/music/music__suno_audio_332200_3_1838718.mp3 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
samples/music/music__suno_audio_196211_4_1844520.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 51 |
samples/music/music__suno_audio_298525_3_1855480.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 52 |
samples/music/music__suno_audio_332200_3_1838718.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
samples/freesound/audio_203313_391226.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
samples/freesound/audio_206738_390405.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
samples/freesound/audio_312332_389459.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
samples/freesound/audio_360573_395201.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
samples/freesound/audio_389654_399191.mp3 filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
samples/freesound/audio_41515_397745.mp3 filter=lfs diff=lfs merge=lfs -text
|
samples/freesound/audio_203313_391226.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_203313_391226.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Waves, surf",
|
| 7 |
+
"confidence": 0.382324
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Ocean",
|
| 11 |
+
"confidence": 0.348145
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Speech",
|
| 15 |
+
"confidence": 0.219971
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "The audio captures the sounds of a large vehicle, likely a bus or truck, including engine noise, air brakes, and a distinct whoosh sound, indicating movement. The soundscape suggests a large commercial vehicle, such as a bus or truck, in motion, possibly passing by or idling. The prominent air brake sound is a clear indicator of its operation."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_203313_391226.mp3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:956a71925011be93db935f6c889f9f82673190e926b182b68fe8fa519aa88d64
|
| 3 |
+
size 1404045
|
samples/freesound/audio_206738_390405.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_206738_390405.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Chink, clink",
|
| 7 |
+
"confidence": 0.403076
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Music",
|
| 11 |
+
"confidence": 0.128174
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Tubular bells",
|
| 15 |
+
"confidence": 0.090088
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "The audio features a continuous, high-pitched, and somewhat distorted electronic sound, resembling a siren or a high-frequency alarm. It has a rhythmic, almost pulsating quality, with a distinct, repetitive pattern. The sound is loud and sustained. This sound is characteristic of an alarm or warning signal, possibly from a fire alarm, a security system, or a warning siren. The repetitive and high-pitched nature suggests an ongoing alert or a continuous warning."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_206738_390405.mp3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66fbf9bb64b37c6f9ad599809a0239c5d8dedba24a4e92d59f0b68bd5f18714d
|
| 3 |
+
size 165069
|
samples/freesound/audio_206747_390848.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_206747_390848.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Ding",
|
| 7 |
+
"confidence": 0.803223
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Clang",
|
| 11 |
+
"confidence": 0.445068
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Ding-dong",
|
| 15 |
+
"confidence": 0.023148
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "The audio features a single, clear, and resonant bell sound. The sound is bright and metallic, with a distinct attack and a long, decaying sustain. This is the sound of a bell being struck, likely a small handbell or a chime. It could be used as a notification sound, a signal, or a simple percussive element in music."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_206747_390848.mp3
ADDED
|
Binary file (22.9 kB). View file
|
|
|
samples/freesound/audio_238707_393020.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_238707_393020.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Door",
|
| 7 |
+
"confidence": 0.127563
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Silence",
|
| 11 |
+
"confidence": 0.071716
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Thunk",
|
| 15 |
+
"confidence": 0.051361
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": ", A sharp, percussive sound, possibly a gunshot or a gunshot, with a distinct metallic resonance."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_238707_393020.mp3
ADDED
|
Binary file (41.9 kB). View file
|
|
|
samples/freesound/audio_312332_389459.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_312332_389459.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Water tap, faucet",
|
| 7 |
+
"confidence": 0.879883
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Sink (filling or washing)",
|
| 11 |
+
"confidence": 0.876465
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Water",
|
| 15 |
+
"confidence": 0.797852
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "The audio features a distinct, high-pitched squeaking sound, characteristic of a squeaky wheel, followed by a series of softer, repetitive squeaks. These sounds are consistent and rhythmic, suggesting a mechanical source. The sounds are clear and appear to be close to the recording device. The sounds strongly suggest the operation of a mechanical device, specifically a squeaky wheel, possibly a cart, a trolley, or a similar piece of machinery. The repetitive nature of the squeaks indicates continuous motion."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_312332_389459.mp3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd4971cb5785ccdabb54581e73b45a64dc44e2380abd3f75e209242bb6bf4f68
|
| 3 |
+
size 244989
|
samples/freesound/audio_315277_393270.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_315277_393270.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Biting",
|
| 7 |
+
"confidence": 0.583008
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Chewing, mastication",
|
| 11 |
+
"confidence": 0.537109
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Crunch",
|
| 15 |
+
"confidence": 0.345459
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "The audio features the distinct sound of a squeaky toy, characterized by a high-pitched, repetitive squeak. The squeak is short and sharp, occurring in quick succession. This sound is indicative of a toy being squeezed, likely a rubber or plastic toy, due to the squeaking noise. It suggests a playful or exploratory action."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_315277_393270.mp3
ADDED
|
Binary file (96.8 kB). View file
|
|
|
samples/freesound/audio_360573_395201.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_360573_395201.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Pink noise",
|
| 7 |
+
"confidence": 0.469482
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Rain",
|
| 11 |
+
"confidence": 0.334961
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Rain on surface",
|
| 15 |
+
"confidence": 0.147461
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "A vehicle, likely a car, driving on a road, with engine noise and tire sounds. The audio captures the distinct sounds of a vehicle in motion, including engine noise and tire sounds, suggesting a car driving on a road."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_360573_395201.mp3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2aa185475fe2faed50cac8ee323ce4938b75cfa36ad249e7e099d72d5ff9b2a5
|
| 3 |
+
size 1069677
|
samples/freesound/audio_389654_399191.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_389654_399191.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Insect",
|
| 7 |
+
"confidence": 0.881836
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Cricket",
|
| 11 |
+
"confidence": 0.869629
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Bird",
|
| 15 |
+
"confidence": 0.018768
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "The audio features a variety of bird vocalizations, including chirps, calls, and possibly some high-pitched calls. The sounds are varied in their timbre and rhythm, suggesting multiple birds or a group of birds. This is a recording of birds in their natural habitat, likely a forest, garden, or park. The variety of calls and chirps suggests a diverse bird population, possibly communicating with each other or calling for each other."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_389654_399191.mp3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6770f06cba6d9aa3bb1da8ae7cfd3d60ca5c70974296f3d8d37faef256abe9d9
|
| 3 |
+
size 616509
|
samples/freesound/audio_391770_402152.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_391770_402152.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Sine wave",
|
| 7 |
+
"confidence": 0.48999
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Beep, bleep",
|
| 11 |
+
"confidence": 0.272217
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Chirp tone",
|
| 15 |
+
"confidence": 0.092041
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "The audio features a single, distinct, high-pitched electronic beep. The sound is brief and clear, with a consistent tone and no discernible modulation. This is a simple electronic alert or notification sound, commonly used as an indicator or a simple signal."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_391770_402152.mp3
ADDED
|
Binary file (4.37 kB). View file
|
|
|
samples/freesound/audio_41515_397745.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": "1.0",
|
| 3 |
+
"audio_file": "audio_41515_397745.mp3",
|
| 4 |
+
"audioset_top3": [
|
| 5 |
+
{
|
| 6 |
+
"label": "Vehicle",
|
| 7 |
+
"confidence": 0.628906
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"label": "Field recording",
|
| 11 |
+
"confidence": 0.505371
|
| 12 |
+
},
|
| 13 |
+
{
|
| 14 |
+
"label": "Train",
|
| 15 |
+
"confidence": 0.168091
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
+
"route": "sfx",
|
| 19 |
+
"annotations": {
|
| 20 |
+
"sound_effect_caption": "A low, continuous hum with a distinct, rhythmic pulsing or throbbing sound. The sound suggests the operation of a large, powerful machine or vehicle, possibly a train or heavy industrial equipment, characterized by a rhythmic pulsing and a deep, resonant hum."
|
| 21 |
+
},
|
| 22 |
+
"error": null
|
| 23 |
+
}
|
samples/freesound/audio_41515_397745.mp3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:008240b34c8b0458ec1419e5e99d802976a9cd66d526f54c172e56016275ab1c
|
| 3 |
+
size 1564317
|
samples/freesound/upstream_captions.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_206747_390848.mp3": {
|
| 3 |
+
"freesound_id": 302960,
|
| 4 |
+
"username": "modularsamples",
|
| 5 |
+
"comprehensive_caption": "A distinct, singular bell-like tone is heard. The tone is clear, resonant, and sustained, with a slight, gentle vibrato or shimmer in its decay, characteristic of a struck metal or crystal object. This sound is likely an electronic chime, a digital notification, or a sound effect mimicking a real-world bell or crystal. Its singular, clear nature suggests it could serve as an alert, an indicator of a completed action, or a short musical flourish.",
|
| 6 |
+
"duration_ms": 1800
|
| 7 |
+
},
|
| 8 |
+
"audio_312332_389459.mp3": {
|
| 9 |
+
"freesound_id": 232905,
|
| 10 |
+
"username": "Ottomaani138",
|
| 11 |
+
"comprehensive_caption": "The audio begins with a distinct \"plop\" sound, followed by the continuous presence of running water, similar to a tap or faucet. Concurrent with the running water, there are intermittent metallic clanking sounds, possibly from pipes or fixtures. Throughout, a soft, bubbly gurgling noise is also audible, indicating water movement in a drain or confined space. This soundscape depicts activity in a bathroom or kitchen setting, specifically related to plumbing. The combination of water running, metallic clanking, and gurgling strongly suggests the operation of a sink, bath, or toilet, with water flowing and potentially draining.",
|
| 12 |
+
"duration_ms": 20271
|
| 13 |
+
},
|
| 14 |
+
"audio_389654_399191.mp3": {
|
| 15 |
+
"freesound_id": 484033,
|
| 16 |
+
"username": "felix.blume",
|
| 17 |
+
"comprehensive_caption": "A rapid series of high-pitched chirping and clicking sounds. These sounds are highly characteristic of insect communication, likely from a cricket or cicada, or possibly a very small bird, indicating natural ambient sounds or the presence of these creatures.",
|
| 18 |
+
"duration_ms": 51246
|
| 19 |
+
},
|
| 20 |
+
"audio_315277_393270.mp3": {
|
| 21 |
+
"freesound_id": 586579,
|
| 22 |
+
"username": "yake01",
|
| 23 |
+
"comprehensive_caption": "Chewing. The distinct sounds of crunching and squishing indicate someone is eating, likely chewing on food.",
|
| 24 |
+
"duration_ms": 7956
|
| 25 |
+
},
|
| 26 |
+
"audio_391770_402152.mp3": {
|
| 27 |
+
"freesound_id": 470772,
|
| 28 |
+
"username": "lilithvf1998",
|
| 29 |
+
"comprehensive_caption": "The audio features a very short, sharp, and distinct high-pitched \"click\" sound. Similar to File 2, this is a precise, discrete sound, likely from the activation of a switch, a button press, or a small mechanical action. It signifies a singular, brief event.",
|
| 30 |
+
"duration_ms": 250
|
| 31 |
+
},
|
| 32 |
+
"audio_41515_397745.mp3": {
|
| 33 |
+
"freesound_id": 194165,
|
| 34 |
+
"username": "Zabuhailo",
|
| 35 |
+
"comprehensive_caption": "The audio features a continuous, low-frequency hum, consistent with the sound of a vehicle engine operating. Throughout the recording, intermittent subtle whirring and mechanical clunking sounds are discernible. The overall hum suggests ongoing movement. Occasional slight shifts in the engine's pitch are present. Towards the end of the recording, a distinct, high-pitched clunk sound is heard, immediately followed by a subtle alteration in the engine's continuous hum. This soundscape depicts travel inside a moving vehicle, most likely a car or a bus. The engine hum and intermittent mechanical sounds suggest the vehicle is in operation, possibly accelerating, decelerating, or encountering varied road conditions, with a distinct mechanical action occurring towards the end.",
|
| 36 |
+
"duration_ms": 130244
|
| 37 |
+
},
|
| 38 |
+
"audio_206738_390405.mp3": {
|
| 39 |
+
"freesound_id": 131443,
|
| 40 |
+
"username": "thecityrings",
|
| 41 |
+
"comprehensive_caption": "A distinct collection of jingling and rattling sounds, characteristic of small metallic objects, is audible. The sounds are irregular and varied, suggesting multiple objects in motion or being handled simultaneously. This audio strongly suggests the movement of keys, coins, or other small metallic items, such as in a pocket or being manipulated by hand.",
|
| 42 |
+
"duration_ms": 13636
|
| 43 |
+
},
|
| 44 |
+
"audio_360573_395201.mp3": {
|
| 45 |
+
"freesound_id": 372559,
|
| 46 |
+
"username": "kijjaz",
|
| 47 |
+
"comprehensive_caption": "The audio is dominated by the continuous, heavy patter of rainfall. The sound is dense and consistent, suggesting a downpour. Intermittently, a low, distant rumbling sound, characteristic of thunder, is also audible. This soundscape depicts a period of intense rain, likely a storm, possibly accompanied by distant thunder. It represents an outdoor environment experiencing significant precipitation.",
|
| 48 |
+
"duration_ms": 89004
|
| 49 |
+
},
|
| 50 |
+
"audio_203313_391226.mp3": {
|
| 51 |
+
"freesound_id": 500392,
|
| 52 |
+
"username": "Ynor9",
|
| 53 |
+
"comprehensive_caption": "Motorcycle engine sounds. The audio primarily features a motorcycle, with distinct sounds of its engine idling, revving, and then accelerating, indicating the vehicle is starting and moving.",
|
| 54 |
+
"duration_ms": 116886
|
| 55 |
+
},
|
| 56 |
+
"audio_238707_393020.mp3": {
|
| 57 |
+
"freesound_id": 151133,
|
| 58 |
+
"username": "RobertMThomas",
|
| 59 |
+
"comprehensive_caption": "A sharp, percussive \"thwack\" sound. This could indicate an object hitting another surface quickly and with some force, such as a slap, a strike, or a quick impact.",
|
| 60 |
+
"duration_ms": 3367
|
| 61 |
+
}
|
| 62 |
+
}
|