Automatic Speech Recognition
NeMo
Safetensors
PyTorch
nemo_speechlm
nvidia
nemotron-3.5
speech
asr
speech-translation
speaker-diarization
audio
transcription
speech-to-text
multilingual
timestamps
long-form-audio
language-identification
code-switching
audio-question-answering
instruction-following
hf-asr-leaderboard
nvfp4
8-bit precision
modelopt
Instructions to use nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Download hero.png from nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4: direct link, hf CLI and curl.
- Browser
- Download file 175 kB
-
https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4/resolve/main/hero.png
- Command line
-
hf download hf://nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4/hero.png
-
curl -L -o hero.png https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4/resolve/main/hero.png
175 kB

- Xet hash:
- 293ca3ebadc564cbb8a08f7221be2d57b05ccaf76d1eb5d8da2f3f6ccf52ef8d
- Size of remote file:
- 175 kB
- SHA256:
- a7a120da10970753a539fc8426238bab866725ce75cf4e2b54d3a5dd75948efc
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.