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: available in Transformers 5.13.0
#23
by eustlb HF Staff - opened
README.md
CHANGED
|
@@ -416,10 +416,10 @@ Here, chunk size = current frame + right context; each chunk is processed in non
|
|
| 416 |
|
| 417 |
This checkpoint also runs with [🤗 Transformers](https://github.com/huggingface/transformers). The target language is passed through the processor's `language` argument: a locale such as `en-US`/`de-DE`, a bare code such as `de`, or `auto` for automatic language detection. In `auto` mode the model appends an `<xx-XX>` language tag after the transcript's terminal punctuation; it is a special token, so decoding with `skip_special_tokens=True` strips it (clean transcript) and `skip_special_tokens=False` keeps it for language labeling.
|
| 418 |
|
| 419 |
-
|
| 420 |
|
| 421 |
```bash
|
| 422 |
-
pip install
|
| 423 |
```
|
| 424 |
|
| 425 |
<details>
|
|
|
|
| 416 |
|
| 417 |
This checkpoint also runs with [🤗 Transformers](https://github.com/huggingface/transformers). The target language is passed through the processor's `language` argument: a locale such as `en-US`/`de-DE`, a bare code such as `de`, or `auto` for automatic language detection. In `auto` mode the model appends an `<xx-XX>` language tag after the transcript's terminal punctuation; it is a special token, so decoding with `skip_special_tokens=True` strips it (clean transcript) and `skip_special_tokens=False` keeps it for language labeling.
|
| 418 |
|
| 419 |
+
Nemotron3_5Asr is available in 🤗 Transformers starting from v5.13.0.
|
| 420 |
|
| 421 |
```bash
|
| 422 |
+
pip install "transformers>=5.13.0"
|
| 423 |
```
|
| 424 |
|
| 425 |
<details>
|