Update app.py

app.py

@@ -21,6 +21,10 @@ models_ru = {
     for name in [
         "gigaam-v2-ctc",
         "gigaam-v2-rnnt",
+        "gigaam-v3-ctc",
+        "gigaam-v3-rnnt",
+        "gigaam-v3-e2e-ctc",
+        "gigaam-v3-e2e-rnnt",
         "nemo-fastconformer-ru-ctc",
         "nemo-fastconformer-ru-rnnt",
         "alphacep/vosk-model-ru",
@@ -99,7 +103,7 @@ def recognize_with_vad(audio: tuple[int, np.ndarray], name: str):
 
 
 with gr.Blocks() as recognize_short:
-    audio = gr.Audio(min_length=1, max_length=30)
+    audio = gr.Audio(validator=lambda audio: gr.validators.is_audio_correct_length(audio, min_length=1, max_length=30))
     with gr.Row():
         gr.ClearButton(audio)
         btn_ru = gr.Button("Recognize (ru)", variant="primary")
@@ -112,7 +116,7 @@ with gr.Blocks() as recognize_short:
 with gr.Blocks() as recognize_long:
     gr.Markdown("The default VAD parameters are used. For best results, you should adjust the VAD parameters in your app.")
     name = gr.Dropdown(models_vad.keys(), label="Model")
-    audio = gr.Audio(min_length=1, max_length=300)
+    audio = gr.Audio(validator=lambda audio: gr.validators.is_audio_correct_length(audio, min_length=1, max_length=300))
     with gr.Row():
         gr.ClearButton(audio)
         btn = gr.Button("Recognize", variant="primary")
@@ -135,7 +139,7 @@ with gr.Blocks(title="onnx-asr demo") as demo:
     # ASR demo using onnx-asr
     **[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 (no `pytorch` or `transformers`).
-    Supports Parakeet TDT 0.6B V2 (En), Parakeet TDT 0.6B V3 (Multilingual) and GigaAM v2 (Ru) models 
+    Supports Parakeet TDT 0.6B V2 (En), Parakeet TDT 0.6B V3 (Multilingual) and GigaAM v2/v3 (Ru) models
     (and many other modern [models](https://github.com/istupakov/onnx-asr?tab=readme-ov-file#supported-model-names)).
     You can also use it with your own model if it has a supported architecture.
     """)
@@ -151,6 +155,10 @@ with gr.Blocks(title="onnx-asr demo") as demo:
         ## Russian ASR models
         * `gigaam-v2-ctc` - Sber GigaAM v2 CTC ([origin](https://github.com/salute-developers/GigaAM), [onnx](https://huggingface.co/istupakov/gigaam-v2-onnx))
         * `gigaam-v2-rnnt` - Sber GigaAM v2 RNN-T ([origin](https://github.com/salute-developers/GigaAM), [onnx](https://huggingface.co/istupakov/gigaam-v2-onnx))
+        * `gigaam-v3-ctc` - Sber GigaAM v3 CTC ([origin](https://huggingface.co/ai-sage/GigaAM-v3), [onnx](https://huggingface.co/istupakov/gigaam-v3-onnx))
+        * `gigaam-v3-rnnt` - Sber GigaAM v3 RNN-T ([origin](https://huggingface.co/ai-sage/GigaAM-v3), [onnx](https://huggingface.co/istupakov/gigaam-v3-onnx))
+        * `gigaam-v3-e2e-ctc` - Sber GigaAM v3 E2E CTC ([origin](https://huggingface.co/ai-sage/GigaAM-v3), [onnx](https://huggingface.co/istupakov/gigaam-v3-onnx))
+        * `gigaam-v3-e2e-rnnt` - Sber GigaAM v3 E2E RNN-T ([origin](https://huggingface.co/ai-sage/GigaAM-v3), [onnx](https://huggingface.co/istupakov/gigaam-v3-onnx))
         * `nemo-fastconformer-ru-ctc` - Nvidia FastConformer-Hybrid Large (ru) with CTC decoder ([origin](https://huggingface.co/nvidia/stt_ru_fastconformer_hybrid_large_pc), [onnx](https://huggingface.co/istupakov/stt_ru_fastconformer_hybrid_large_pc_onnx))
         * `nemo-fastconformer-ru-rnnt` - Nvidia FastConformer-Hybrid Large (ru) with RNN-T decoder ([origin](https://huggingface.co/nvidia/stt_ru_fastconformer_hybrid_large_pc), [onnx](https://huggingface.co/istupakov/stt_ru_fastconformer_hybrid_large_pc_onnx))
         * `nemo-parakeet-tdt-0.6b-v3` - Nvidia Parakeet TDT 0.6B V3 (multilingual) ([origin](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3), [onnx](https://huggingface.co/istupakov/parakeet-tdt-0.6b-v3-onnx))