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

DedeProGames
/
SoralASR-23M-Preview

Automatic Speech Recognition
Transformers
Safetensors
English
whisper
asr
english
from-scratch
small-model
Eval Results
Model card Files Files and versions
xet
Community
1

Instructions to use DedeProGames/SoralASR-23M-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use DedeProGames/SoralASR-23M-Preview with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("automatic-speech-recognition", model="DedeProGames/SoralASR-23M-Preview")
    # pip install -U transformers accelerate
    # Load model directly
    from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
    
    processor = AutoProcessor.from_pretrained("DedeProGames/SoralASR-23M-Preview")
    model = AutoModelForSpeechSeq2Seq.from_pretrained("DedeProGames/SoralASR-23M-Preview", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
SoralASR-23M-Preview
465 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 57 commits
DedeProGames's picture
DedeProGames
Document self-reported WER splits and leaderboard publication
91f8975 verified 24 days ago
  • .eval_results
    Document self-reported WER splits and leaderboard publication 24 days ago
  • checkpoints
    Training checkpoint step 50000 (before-evaluation) 24 days ago
  • .gitattributes
    1.52 kB
    initial commit 25 days ago
  • README.md
    9.73 kB
    Clarify self-reported ASR results and leaderboard status 24 days ago
  • added_tokens.json
    34.6 kB
    Publish SoralASR-23M at step 50000 24 days ago
  • config.json
    1.22 kB
    Fix encoder layer count to load all five trained layers 24 days ago
  • generation_config.json
    18 kB
    Publish SoralASR-23M at step 50000 24 days ago
  • merges.txt
    456 kB
    Publish SoralASR-23M at step 50000 24 days ago
  • model.safetensors
    92.3 MB
    xet
    Publish SoralASR-23M at step 50000 24 days ago
  • normalizer.json
    52.7 kB
    Publish SoralASR-23M at step 50000 24 days ago
  • preprocessor_config.json
    356 Bytes
    Publish SoralASR-23M at step 50000 24 days ago
  • special_tokens_map.json
    2.17 kB
    Publish SoralASR-23M at step 50000 24 days ago
  • tokenizer_config.json
    283 kB
    Publish SoralASR-23M at step 50000 24 days ago
  • training_metrics.json
    452 Bytes
    Publish SoralASR-23M at step 50000 24 days ago
  • vocab.json
    999 kB
    Publish SoralASR-23M at step 50000 24 days ago