Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

ernensbjorn
/
perch-v2-int8-tflite

Audio Classification
LiteRT
English
audio
bird
bioacoustics
wildlife
quantized
int8
float16
raspberry-pi
edge-ai
perch
Model card Files Files and versions
xet
Community
perch-v2-int8-tflite
720 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 7 commits
ernensbjorn's picture
ernensbjorn
Replace old int8 model with 3 properly optimized variants (original, fp16, dynint8) converted from official Google SavedModel
71fd62f verified 6 months ago
  • .gitattributes
    1.52 kB
    initial commit 6 months ago
  • README.md
    6.14 kB
    Replace old int8 model with 3 properly optimized variants (original, fp16, dynint8) converted from official Google SavedModel 6 months ago
  • bird_indices.json
    64.7 kB
    Replace old int8 model with 3 properly optimized variants (original, fp16, dynint8) converted from official Google SavedModel 6 months ago
  • labels.txt
    313 kB
    Replace old int8 model with 3 properly optimized variants (original, fp16, dynint8) converted from official Google SavedModel 6 months ago
  • perch_v2_dynint8.tflite
    105 MB
    xet
    Replace old int8 model with 3 properly optimized variants (original, fp16, dynint8) converted from official Google SavedModel 6 months ago
  • perch_v2_fp16.tflite
    205 MB
    xet
    Replace old int8 model with 3 properly optimized variants (original, fp16, dynint8) converted from official Google SavedModel 6 months ago
  • perch_v2_original.tflite
    409 MB
    xet
    Replace old int8 model with 3 properly optimized variants (original, fp16, dynint8) converted from official Google SavedModel 6 months ago