Update README.md
Browse files
README.md
CHANGED
|
@@ -1,21 +1,19 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
-
license_name: nvidia-open-model-license
|
| 4 |
-
license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
|
| 5 |
library_name: coreml
|
| 6 |
base_model: nvidia/nemotron-speech-streaming-en-0.6b
|
| 7 |
tags:
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
pipeline_tag: automatic-speech-recognition
|
| 20 |
---
|
| 21 |
# Sortformer CoreML Models
|
|
@@ -149,5 +147,4 @@ https://github.com/FluidInference/FluidAudio/blob/main/Documentation/Benchmarks.
|
|
| 149 |
- Build & Optimization: Engineering the static shape configurations that allow the model to achieve ~120x RTF on Apple Silicon.
|
| 150 |
- Logic Implementation: Porting the critical streaming state logic (speaker cache and FIFO management) to ensure consistent speaker identity tracking.
|
| 151 |
|
| 152 |
-
This project was built upon the foundational work of the NVIDIA NeMo team.
|
| 153 |
-
|
|
|
|
| 1 |
---
|
| 2 |
+
license: cc-by-4.0
|
|
|
|
|
|
|
| 3 |
library_name: coreml
|
| 4 |
base_model: nvidia/nemotron-speech-streaming-en-0.6b
|
| 5 |
tags:
|
| 6 |
+
- speech-recognition
|
| 7 |
+
- automatic-speech-recognition
|
| 8 |
+
- streaming-asr
|
| 9 |
+
- coreml
|
| 10 |
+
- apple
|
| 11 |
+
- ios
|
| 12 |
+
- macos
|
| 13 |
+
- FastConformer
|
| 14 |
+
- RNNT
|
| 15 |
+
- Parakeet
|
| 16 |
+
- ASR
|
| 17 |
pipeline_tag: automatic-speech-recognition
|
| 18 |
---
|
| 19 |
# Sortformer CoreML Models
|
|
|
|
| 147 |
- Build & Optimization: Engineering the static shape configurations that allow the model to achieve ~120x RTF on Apple Silicon.
|
| 148 |
- Logic Implementation: Porting the critical streaming state logic (speaker cache and FIFO management) to ensure consistent speaker identity tracking.
|
| 149 |
|
| 150 |
+
This project was built upon the foundational work of the NVIDIA NeMo team.
|
|
|