Automatic Speech Recognition
NeMo
Safetensors
PyTorch
Transformers
English
parakeet_rnnt
feature-extraction
speech
audio
Transducer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use nvidia/parakeet-rnnt-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/parakeet-rnnt-0.6b with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-rnnt-0.6b") transcriptions = asr_model.transcribe(["file.wav"]) - Transformers
How to use nvidia/parakeet-rnnt-0.6b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nvidia/parakeet-rnnt-0.6b")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/parakeet-rnnt-0.6b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload ParakeetForRNNT
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -33,11 +33,11 @@
|
|
| 33 |
"hidden_act": "relu",
|
| 34 |
"initializer_range": 0.02,
|
| 35 |
"is_encoder_decoder": true,
|
|
|
|
| 36 |
"max_symbols_per_step": 10,
|
| 37 |
"model_type": "parakeet_rnnt",
|
| 38 |
"num_decoder_layers": 2,
|
| 39 |
"pad_token_id": 0,
|
| 40 |
-
"rnnt_loss_reduction": "mean_volume",
|
| 41 |
"transformers_version": "5.10.0.dev0",
|
| 42 |
"vocab_size": 1025
|
| 43 |
}
|
|
|
|
| 33 |
"hidden_act": "relu",
|
| 34 |
"initializer_range": 0.02,
|
| 35 |
"is_encoder_decoder": true,
|
| 36 |
+
"loss_reduction": "mean_volume",
|
| 37 |
"max_symbols_per_step": 10,
|
| 38 |
"model_type": "parakeet_rnnt",
|
| 39 |
"num_decoder_layers": 2,
|
| 40 |
"pad_token_id": 0,
|
|
|
|
| 41 |
"transformers_version": "5.10.0.dev0",
|
| 42 |
"vocab_size": 1025
|
| 43 |
}
|