Downloads · 30 days
50
30% of all-time downloads
nemotron-3.5-asr-hebrew-streaming-0.6b
notmax123/nemotron-3.5-asr-hebrew-streaming-0.6b
nemotron-3.5-asr-hebrew-streaming-0.6b is a automatic speech recognition model from notmax123. Use it when you need speech turned into text. It is set up for nemo. The card lists the license as apache-2.0.
Fine-tuned nvidia/nemotron-3.5-asr-streaming-0.6b for Hebrew (he-IL) cache-aware streaming ASR.
All-time downloads
169
Public
Repo size
2.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.nemo2.6 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Access
- Public
- Created
- Jul 6, 2026
- Updated
- Jul 6, 2026
- SHA
- 8c52f4f9
Base models
Model card
From the Hugging Face model README
Nemotron 3.5 ASR Hebrew Streaming 0.6B
Fine-tuned nvidia/nemotron-3.5-asr-streaming-0.6b for Hebrew (he-IL) cache-aware streaming ASR.
Model details
| Base model | nvidia/nemotron-3.5-asr-streaming-0.6b |
| Architecture | FastConformer-Transducer (RNNT) with langID prompt conditioning |
| Language | Hebrew (he-IL, prompt_mode=langID) |
| Sample rate | 16 kHz |
| Streaming | Cache-aware; deployment latency ~80 ms (att_context_size=[56,0]) |
| Dev val WER | 17.41% (VoxKnesset hold-out dev) |
| Format | NeMo .nemo checkpoint (~2.4 GB) |
Training
Fine-tuned following the NVIDIA Nemotron 3.5 ASR fine-tuning guide on Hebrew speech data (VoxKnesset, synthetic TTS, podcasts, ivrit.ai sources). Training uses Lhotse bucketing, bf16, NoamAnnealing, and telephony-style augmentations (noise, gain, SpecAugment).
Usage
NeMo (recommended)
import nemo.collections.asr as nemo_asr
model = nemo_asr.models.ASRModel.restore_from(
"nemotron-3.5-asr-hebrew-streaming-0.6b.nemo"
)
# Offline transcription with Hebrew langID prompt
hypotheses = model.transcribe(
["audio.wav"],
batch_size=1,
verbose=False,
)
print(hypotheses[0].text)
For streaming inference, use cache-aware streaming with att_context_size=[56, 0] as in the base model card.
Download
hf download notmax123/nemotron-3.5-asr-hebrew-streaming-0.6b
Limitations
- Optimized for Hebrew; other languages are not supported by this checkpoint.
- Long audio should be chunked for streaming evaluation (see project eval scripts).
- Intended for research and production ASR; verify on your domain before deployment.
License
Apache 2.0 (same as the base Nemotron 3.5 ASR model).
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Languages
- he
- Created
- Jul 6, 2026
- Updated
- Jul 6, 2026