Automatic Speech Recognition
NeMo
Safetensors
Transformers
PyTorch
nemotron3_5_asr
feature-extraction
speech-recognition
cache-aware ASR
streaming-asr
multilingual
speech
audio
FastConformer
RNNT
Parakeet
ASR
NeMo
Eval Results (legacy)
Eval Results
Instructions to use nvidia/nemotron-3.5-asr-streaming-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/nemotron-3.5-asr-streaming-0.6b with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/nemotron-3.5-asr-streaming-0.6b") transcriptions = asr_model.transcribe(["file.wav"]) - Transformers
How to use nvidia/nemotron-3.5-asr-streaming-0.6b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nvidia/nemotron-3.5-asr-streaming-0.6b")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("nvidia/nemotron-3.5-asr-streaming-0.6b") model = AutoModel.from_pretrained("nvidia/nemotron-3.5-asr-streaming-0.6b", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update README.md
#13
by linyuan2001 - opened
README.md
CHANGED
|
@@ -1,45 +1,12 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
license_name: openmdw-1.1
|
| 4 |
-
license_link:
|
| 5 |
-
https://openmdw.ai/license/1-1/
|
| 6 |
library_name: nemo
|
| 7 |
language:
|
| 8 |
- en
|
| 9 |
-
- es
|
| 10 |
-
- de
|
| 11 |
-
- fr
|
| 12 |
-
- it
|
| 13 |
-
- ar
|
| 14 |
- ja
|
| 15 |
-
- ko
|
| 16 |
-
- pt
|
| 17 |
-
- ru
|
| 18 |
-
- hi
|
| 19 |
-
- zh
|
| 20 |
- vi
|
| 21 |
-
- he
|
| 22 |
-
- nl
|
| 23 |
-
- cs
|
| 24 |
-
- da
|
| 25 |
-
- pl
|
| 26 |
-
- 'no'
|
| 27 |
-
- sv
|
| 28 |
-
- th
|
| 29 |
-
- tr
|
| 30 |
-
- bg
|
| 31 |
-
- el
|
| 32 |
-
- et
|
| 33 |
-
- fi
|
| 34 |
-
- hr
|
| 35 |
-
- hu
|
| 36 |
-
- lt
|
| 37 |
-
- lv
|
| 38 |
-
- ro
|
| 39 |
-
- sk
|
| 40 |
-
- uk
|
| 41 |
-
- mt
|
| 42 |
-
- sl
|
| 43 |
datasets:
|
| 44 |
- nvidia/Granary
|
| 45 |
- multilingual_librispeech
|
|
@@ -168,7 +135,10 @@ model-index:
|
|
| 168 |
value: 7.12
|
| 169 |
metrics:
|
| 170 |
- wer
|
| 171 |
-
pipeline_tag:
|
|
|
|
|
|
|
|
|
|
| 172 |
---
|
| 173 |
|
| 174 |
# Nemotron 3.5 ASR
|
|
@@ -590,4 +560,4 @@ NVIDIA believes Trustworthy AI is a shared responsibility and we have establishe
|
|
| 590 |
|
| 591 |
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
|
| 592 |
|
| 593 |
-
---
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
license_name: openmdw-1.1
|
| 4 |
+
license_link: https://openmdw.ai/license/1-1/
|
|
|
|
| 5 |
library_name: nemo
|
| 6 |
language:
|
| 7 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
- ja
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
- vi
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
datasets:
|
| 11 |
- nvidia/Granary
|
| 12 |
- multilingual_librispeech
|
|
|
|
| 135 |
value: 7.12
|
| 136 |
metrics:
|
| 137 |
- wer
|
| 138 |
+
pipeline_tag: audio-text-to-text
|
| 139 |
+
base_model:
|
| 140 |
+
- google/gemma-4-12B-it
|
| 141 |
+
- openai/gpt-oss-20b
|
| 142 |
---
|
| 143 |
|
| 144 |
# Nemotron 3.5 ASR
|
|
|
|
| 560 |
|
| 561 |
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).
|
| 562 |
|
| 563 |
+
---
|