Create app.py

.gitignore

@@ -0,0 +1 @@
+env/

.ipynb_checkpoints/app-checkpoint.py

@@ -0,0 +1,49 @@
+# Gaepago model V1 (CPU Test)
+
+# import package
+from transformers import AutoModelForAudioClassification
+from transformers import AutoFeatureExtractor
+from transformers import pipeline
+import gradio as gr
+import torch
+
+# Set model & Dataset NM
+MODEL_NAME = "Gae8J/gaepago-20"
+DATASET_NAME = "Gae8J/modeling_v1"
+
+# Import Model & feature extractor
+model = AutoModelForAudioClassification.from_pretrained(MODEL_NAME)
+feature_extractor = AutoFeatureExtractor.from_pretrained(MODEL_NAME)
+
+# 모델 cpu로 변경하여 진행
+model.to("cpu")
+
+# Gaepago Inference Model function
+def gaepago_fn(tmp_audio_dir):
+    print(tmp_audio_dir)
+    audio_dataset = Dataset.from_dict({"audio": [tmp_audio_dir]}).cast_column("audio", Audio(sampling_rate=16000))
+    inputs = feature_extractor(audio_dataset[0]["audio"]["array"]
+                               ,sampling_rate=audio_dataset[0]["audio"]["sampling_rate"]
+                               ,return_tensors="pt")
+    with torch.no_grad():
+        logits = model(**inputs).logits
+    predicted_class_ids = torch.argmax(logits).item()
+    predicted_label = model.config.id2label[predicted_class_ids]
+    
+    return predicted_label
+
+# Main
+main_api = gr.Blocks()
+
+with demo:
+    gr.Markdown("## 8J Gaepago Demo(with CPU)")
+    with gr.Row():
+        audio = gr.Audio(source="microphone", type="filepath"
+                         ,label='녹음버튼을 눌러 초코가 하는 말을 들려주세요')
+        transcription = gr.Textbox(label='지금 초코가 하는 말은...')
+    b1 = gr.Button("강아지 언어 번역!")
+
+    b1.click(gaepago_fn, inputs=audio, outputs=transcription)
+    examples = gr.Examples(examples=example_list,
+                           inputs=[audio])
+main_api.launch(share=True)

app.py

@@ -0,0 +1,49 @@
+# Gaepago model V1 (CPU Test)
+
+# import package
+from transformers import AutoModelForAudioClassification
+from transformers import AutoFeatureExtractor
+from transformers import pipeline
+import gradio as gr
+import torch
+
+# Set model & Dataset NM
+MODEL_NAME = "Gae8J/gaepago-20"
+DATASET_NAME = "Gae8J/modeling_v1"
+
+# Import Model & feature extractor
+model = AutoModelForAudioClassification.from_pretrained(MODEL_NAME)
+feature_extractor = AutoFeatureExtractor.from_pretrained(MODEL_NAME)
+
+# 모델 cpu로 변경하여 진행
+model.to("cpu")
+
+# Gaepago Inference Model function
+def gaepago_fn(tmp_audio_dir):
+    print(tmp_audio_dir)
+    audio_dataset = Dataset.from_dict({"audio": [tmp_audio_dir]}).cast_column("audio", Audio(sampling_rate=16000))
+    inputs = feature_extractor(audio_dataset[0]["audio"]["array"]
+                               ,sampling_rate=audio_dataset[0]["audio"]["sampling_rate"]
+                               ,return_tensors="pt")
+    with torch.no_grad():
+        logits = model(**inputs).logits
+    predicted_class_ids = torch.argmax(logits).item()
+    predicted_label = model.config.id2label[predicted_class_ids]
+    
+    return predicted_label
+
+# Main
+main_api = gr.Blocks()
+
+with demo:
+    gr.Markdown("## 8J Gaepago Demo(with CPU)")
+    with gr.Row():
+        audio = gr.Audio(source="microphone", type="filepath"
+                         ,label='녹음버튼을 눌러 초코가 하는 말을 들려주세요')
+        transcription = gr.Textbox(label='지금 초코가 하는 말은...')
+    b1 = gr.Button("강아지 언어 번역!")
+
+    b1.click(gaepago_fn, inputs=audio, outputs=transcription)
+    examples = gr.Examples(examples=example_list,
+                           inputs=[audio])
+main_api.launch(share=True)

requirements.txt

@@ -0,0 +1,89 @@
+aiofiles==23.1.0
+aiohttp==3.8.4
+aiosignal==1.3.1
+altair==5.0.1
+anyio==3.7.0
+async-timeout==4.0.2
+attrs==23.1.0
+certifi==2023.5.7
+charset-normalizer==3.1.0
+click==8.1.3
+cmake==3.26.4
+contourpy==1.1.0
+cycler==0.11.0
+exceptiongroup==1.1.1
+fastapi==0.97.0
+ffmpy==0.3.0
+filelock==3.12.2
+fonttools==4.40.0
+frozenlist==1.3.3
+fsspec==2023.6.0
+gradio==3.35.2
+gradio_client==0.2.7
+h11==0.14.0
+httpcore==0.17.2
+httpx==0.24.1
+huggingface-hub==0.15.1
+idna==3.4
+importlib-resources==5.12.0
+Jinja2==3.1.2
+jsonschema==4.17.3
+kiwisolver==1.4.4
+linkify-it-py==2.0.2
+lit==16.0.6
+markdown-it-py==2.2.0
+MarkupSafe==2.1.3
+matplotlib==3.7.1
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.4
+networkx==3.1
+numpy==1.24.3
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cufft-cu11==10.9.0.58
+nvidia-curand-cu11==10.2.10.91
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-nccl-cu11==2.14.3
+nvidia-nvtx-cu11==11.7.91
+orjson==3.9.1
+packaging==23.1
+pandas==2.0.2
+Pillow==9.5.0
+pkgutil_resolve_name==1.3.10
+pydantic==1.10.9
+pydub==0.25.1
+Pygments==2.15.1
+pyparsing==3.1.0
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3
+PyYAML==6.0
+regex==2023.6.3
+requests==2.31.0
+safetensors==0.3.1
+semantic-version==2.10.0
+six==1.16.0
+sniffio==1.3.0
+starlette==0.27.0
+sympy==1.12
+tokenizers==0.13.3
+toolz==0.12.0
+torch==2.0.1
+tqdm==4.65.0
+transformers==4.30.2
+triton==2.0.0
+typing_extensions==4.6.3
+tzdata==2023.3
+uc-micro-py==1.0.2
+urllib3==2.0.3
+uvicorn==0.22.0
+websockets==11.0.3
+yarl==1.9.2
+zipp==3.15.0