Update app.py
Browse files
app.py
CHANGED
|
@@ -32,7 +32,22 @@ def recoginize(audio: tuple[int, np.ndarray]):
|
|
| 32 |
demo = gr.Interface(
|
| 33 |
fn=recoginize,
|
| 34 |
title="ASR demo using onnx-asr (Russian models)",
|
| 35 |
-
description="""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
## Models used in demo:
|
| 37 |
* `gigaam-v2-ctc` - Sber GigaAM v2 CTC ([origin](https://github.com/salute-developers/GigaAM), [onnx](https://huggingface.co/istupakov/gigaam-v2-onnx))
|
| 38 |
* `gigaam-v2-rnnt` - Sber GigaAM v2 RNN-T ([origin](https://github.com/salute-developers/GigaAM), [onnx](https://huggingface.co/istupakov/gigaam-v2-onnx))
|
|
|
|
| 32 |
demo = gr.Interface(
|
| 33 |
fn=recoginize,
|
| 34 |
title="ASR demo using onnx-asr (Russian models)",
|
| 35 |
+
description="""
|
| 36 |
+
# ONNX ASR
|
| 37 |
+
|
| 38 |
+
[](https://pypi.org/project/onnx-asr)
|
| 39 |
+
[](https://pypi.org/project/onnx-asr)
|
| 40 |
+
[](https://pypi.org/project/onnx-asr)
|
| 41 |
+
[](https://pypi.org/project/onnx-asr)
|
| 42 |
+
[](https://github.com/istupakov/onnx-asr/blob/main/LICENSE)
|
| 43 |
+
[](https://github.com/istupakov/onnx-asr/actions/workflows/python-package.yml)
|
| 44 |
+
|
| 45 |
+
**[onnx-asr](https://github.com/istupakov/onnx-asr)** is a Python package for Automatic Speech Recognition using ONNX models. The package is written in pure Python with minimal dependencies (*PyTorch is not required*):
|
| 46 |
+
|
| 47 |
+
[](https://pypi.org/project/numpy/)
|
| 48 |
+
[](https://pypi.org/project/onnxruntime/)
|
| 49 |
+
[](https://pypi.org/project/huggingface-hub/)
|
| 50 |
+
|
| 51 |
## Models used in demo:
|
| 52 |
* `gigaam-v2-ctc` - Sber GigaAM v2 CTC ([origin](https://github.com/salute-developers/GigaAM), [onnx](https://huggingface.co/istupakov/gigaam-v2-onnx))
|
| 53 |
* `gigaam-v2-rnnt` - Sber GigaAM v2 RNN-T ([origin](https://github.com/salute-developers/GigaAM), [onnx](https://huggingface.co/istupakov/gigaam-v2-onnx))
|