Hugging Face's logo

mazesmazes
/
tiny-audio

Automatic Speech Recognition
Transformers
Safetensors
English
asr_model
asr
speech-recognition
speech-to-text
audio
speech-llm
word-timestamps
speaker-diarization
qwen
granite-speech
lora
custom_code
Eval Results (legacy)
Model card Files
xet
 Community
tiny-audio / README.md

Commit History

10 days ago

  1. Model card: current WER table, eval results (model-index), tags; list AutoModelForSpeechSeq2Seq first in auto_map

    mazesmazes
    Verified signature
    36b481d

11 days ago

  1. Update custom model files, README, and requirements

    mazesmazes
    Verified signature
    3edc078

  2. Upload README.md with huggingface_hub

    mazesmazes
    Verified signature
    eece501

  3. Update custom model files, README, and requirements

    mazesmazes
    Verified signature
    8c0bdcb

12 days ago

  1. Model card: long-audio and diarization limits, credit Nemotron and Qwen aligner

    mazesmazes
    Verified signature
    101b2f0

  2. Update custom model files, README, and requirements

    mazesmazes
    Verified signature
    cf1aff8

  3. Model card: document speaker diarization

    mazesmazes
    Verified signature
    3adc10a

  4. Update model card for granite-qwen-frozen-4

    mazesmazes
    Verified signature
    1c9abe3

  1. Update README from MODEL_CARD.md

    mazesmazes
    Verified signature
    1a57f53

  1. Model save

    mazesmazes
    Verified signature
    648911e

  1. Model save

    mazesmazes
    Verified signature
    5a38762

  1. Model save

    mazesmazes
    Verified signature
    fd72c1b

  1. Training in progress - step 1000

    mazesmazes
    Verified signature
    c5a1720