Automatic Speech Recognition
NeMo
PyTorch
English
speech
audio
CTC
Conformer
Transformer
NeMo
hf-asr-leaderboard
Riva
Eval Results (legacy)
Eval Results
Instructions to use nvidia/stt_en_conformer_ctc_large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/stt_en_conformer_ctc_large with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_en_conformer_ctc_large") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
make images inline
#2
by radames - opened
README.md
CHANGED
|
@@ -146,7 +146,16 @@ model-index:
|
|
| 146 |
|
| 147 |
# NVIDIA Conformer-CTC Large (en-US)
|
| 148 |
|
| 149 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
|
| 151 |
|
| 152 |
This model transcribes speech in lowercase English alphabet including spaces and apostrophes, and is trained on several thousand hours of English speech data.
|
|
|
|
| 146 |
|
| 147 |
# NVIDIA Conformer-CTC Large (en-US)
|
| 148 |
|
| 149 |
+
<style>
|
| 150 |
+
img {
|
| 151 |
+
display: inline;
|
| 152 |
+
}
|
| 153 |
+
</style>
|
| 154 |
+
|
| 155 |
+
| [](#model-architecture)
|
| 156 |
+
| [](#model-architecture)
|
| 157 |
+
| [](#datasets)
|
| 158 |
+
| [](#deployment-with-nvidia-riva) |
|
| 159 |
|
| 160 |
|
| 161 |
This model transcribes speech in lowercase English alphabet including spaces and apostrophes, and is trained on several thousand hours of English speech data.
|