Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

laion
/
sound-effect-captioning-whisper

Automatic Speech Recognition
Transformers
Safetensors
English
whisper
audio-captioning
sound-effect-captioning
audio-description
laion
Model card Files Files and versions
xet
Community
sound-effect-captioning-whisper
972 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
ChristophSchuhmann's picture
ChristophSchuhmann
Upgrade to stage-3 checkpoint (val loss 1.4314, down from 1.4940)
bb36f9c verified about 9 hours ago
  • examples
    Upgrade to stage-3 checkpoint (val loss 1.4314, down from 1.4940) about 9 hours ago
  • .gitattributes
    1.75 kB
    Upgrade to stage-3 checkpoint (val loss 1.4314, down from 1.4940) about 9 hours ago
  • README.md
    16 kB
    Upgrade to stage-3 checkpoint (val loss 1.4314, down from 1.4940) about 9 hours ago
  • config.json
    1.3 kB
    Initial release: sound-effect captioning Whisper (stage-2 best, val loss 1.494) about 15 hours ago
  • generation_config.json
    3.77 kB
    Initial release: sound-effect captioning Whisper (stage-2 best, val loss 1.494) about 15 hours ago
  • model.safetensors
    967 MB
    xet
    Upgrade to stage-3 checkpoint (val loss 1.4314, down from 1.4940) about 9 hours ago
  • preprocessor_config.json
    315 Bytes
    Initial release: sound-effect captioning Whisper (stage-2 best, val loss 1.494) about 15 hours ago
  • processor_config.json
    409 Bytes
    Initial release: sound-effect captioning Whisper (stage-2 best, val loss 1.494) about 15 hours ago
  • tokenizer.json
    3.93 MB
    Initial release: sound-effect captioning Whisper (stage-2 best, val loss 1.494) about 15 hours ago
  • tokenizer_config.json
    2.08 kB
    Initial release: sound-effect captioning Whisper (stage-2 best, val loss 1.494) about 15 hours ago