Automatic Speech Recognition
NeMo
Safetensors
PyTorch
Transformers
nemo_speechlm
text2text-generation
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
Eval Results
Instructions to use nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B 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 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") transcriptions = asr_model.transcribe(["file.wav"]) - Transformers
How to use nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B") model = AutoModelForMultimodalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download serving_performance.png from nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B: direct link, hf CLI and curl.
- Browser
- Download file 50.7 kB
-
https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B/resolve/main/serving_performance.png
- Command line
-
hf download hf://nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B/serving_performance.png
-
curl -L -o serving_performance.png https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B/resolve/main/serving_performance.png
50.7 kB
