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

nvidia
/
nemotron-speech-streaming-en-0.6b

Automatic Speech Recognition
NeMo
Safetensors
GGUF
Transformers
PyTorch
nemotron_asr_streaming
feature-extraction
speech-recognition
cache-aware ASR
streaming-asr
speech
audio
FastConformer
RNNT
Parakeet
ASR
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Model card Files Files and versions
xet
Community
21

Instructions to use nvidia/nemotron-speech-streaming-en-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • NeMo

    How to use nvidia/nemotron-speech-streaming-en-0.6b with NeMo:

    import nemo.collections.asr as nemo_asr
    asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/nemotron-speech-streaming-en-0.6b")
    
    transcriptions = asr_model.transcribe(["file.wav"])
  • Transformers

    How to use nvidia/nemotron-speech-streaming-en-0.6b with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("automatic-speech-recognition", model="nvidia/nemotron-speech-streaming-en-0.6b")
    # Load model directly
    from transformers import AutoProcessor, AutoModel
    
    processor = AutoProcessor.from_pretrained("nvidia/nemotron-speech-streaming-en-0.6b")
    model = AutoModel.from_pretrained("nvidia/nemotron-speech-streaming-en-0.6b", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Built a Linux dictation tool on this model, word by word typing on GNOME Wayland

1
#22 opened 5 days ago by
scottnelsonathome

Certain words are repeated many times more than they are repeated by the speaker

1
#18 opened 2 months ago by
VM1991

Mel-spectrogram boundary artifacts degrade quality in real-time mic streaming — fix inside

🔥👍 2
1
#15 opened 5 months ago by
Twizz

Are there any more metrics or articles on how this compares to other models for streaming?

1
#13 opened 6 months ago by
minimanatee

How about a TDT based version instead of RNN-T?

➕ 5
#12 opened 7 months ago by
yash-levelai

missing punctuation marks

🤗👀 1
#11 opened 7 months ago by
Kerwin11

Can we expect an ONNX quant?

➕ 3
3
#6 opened 7 months ago by
SuperPauly

MLX version planned?

3
#3 opened 8 months ago by
Amit-I

Multilingual version planned?

16
#2 opened 8 months ago by
fosple
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs