Automatic Speech Recognition
NeMo
Safetensors
GGUF
Transformers
PyTorch
English
parakeet_ctc
speech
audio
FastConformer
Conformer
NeMo
hf-asr-leaderboard
ctc
Eval Results (legacy)
Eval Results
Instructions to use nvidia/parakeet-ctc-1.1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/parakeet-ctc-1.1b with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-ctc-1.1b") transcriptions = asr_model.transcribe(["file.wav"]) - Transformers
How to use nvidia/parakeet-ctc-1.1b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nvidia/parakeet-ctc-1.1b")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCTC model = AutoModelForCTC.from_pretrained("nvidia/parakeet-ctc-1.1b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Set layerdrop to 0.0 (the model was trained without stochastic depth)
#5
by Steveeeeeeen HF Staff - opened
- config.json +1 -1
config.json
CHANGED
|
@@ -16,7 +16,7 @@
|
|
| 16 |
"hidden_size": 1024,
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
"intermediate_size": 4096,
|
| 19 |
-
"layerdrop": 0.
|
| 20 |
"max_position_embeddings": 5000,
|
| 21 |
"model_type": "parakeet_encoder",
|
| 22 |
"num_attention_heads": 8,
|
|
|
|
| 16 |
"hidden_size": 1024,
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
"intermediate_size": 4096,
|
| 19 |
+
"layerdrop": 0.0,
|
| 20 |
"max_position_embeddings": 5000,
|
| 21 |
"model_type": "parakeet_encoder",
|
| 22 |
"num_attention_heads": 8,
|