Update README.md
Browse files
README.md
CHANGED
|
@@ -11,4 +11,6 @@ license: bsd-3-clause
|
|
| 11 |
short_description: Speech transcription (Nvidia/parakeet-tdt-0.6b-v3+onnx_asr)
|
| 12 |
---
|
| 13 |
|
| 14 |
-
|
|
|
|
|
|
|
|
|
| 11 |
short_description: Speech transcription (Nvidia/parakeet-tdt-0.6b-v3+onnx_asr)
|
| 12 |
---
|
| 13 |
|
| 14 |
+
This space uses Nvidia [parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) model in [onnx format](https://huggingface.co/istupakov/parakeet-tdt-0.6b-v3-onnx) with [onnx-asr](https://github.com/istupakov/onnx-asr) backend.
|
| 15 |
+
In theory with minor edits it can work both on CPU and GPU but I don't have access to ZeroGPU spaces to enable hardware acceleration.
|
| 16 |
+
Locally I tested it with Nvidia RTX3060 and RTX4060Ti and it used about 6GB VRAM with 150s chunks.
|