speech recognition

.gitignore

@@ -0,0 +1,7 @@
+# .gitignore file for python projects
+.venv
+.env
+__pycache__
+*.pyc
+*.pyo
+*.pyd

app.py

@@ -1,7 +1,26 @@
 import gradio as gr
+from transformers import pipeline
+import numpy as np
 
-def greet(name):
-    return "Hello " + name + "!!"
+transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+def transcribe(stream, new_chunk):
+    sr, y = new_chunk
+    y = y.astype(np.float32)
+    y /= np.max(np.abs(y))
+
+    if stream is not None:
+        stream = np.concatenate([stream, y])
+    else:
+        stream = y
+    return stream, transcriber({"sampling_rate": sr, "raw": stream})["text"]
+
+
+demo = gr.Interface(
+    transcribe,
+    ["state", gr.Audio(sources=["microphone"], streaming=True)],
+    ["state", "text"],
+    live=True,
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,69 @@
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.6.0
+anyio==4.3.0
+attrs==23.2.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+exceptiongroup==1.2.0
+fastapi==0.110.1
+ffmpy==0.3.2
+filelock==3.13.4
+fonttools==4.51.0
+fsspec==2024.3.1
+gradio==4.26.0
+gradio_client==0.15.1
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.22.2
+idna==3.7
+importlib_resources==6.4.0
+Jinja2==3.1.3
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.4
+mdurl==0.1.2
+numpy==1.26.4
+orjson==3.10.0
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+pydantic==2.7.0
+pydantic_core==2.18.1
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.34.0
+regex==2023.12.25
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+ruff==0.3.7
+safetensors==0.4.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+tokenizers==0.15.2
+tomlkit==0.12.0
+toolz==0.12.1
+tqdm==4.66.2
+transformers==4.39.3
+typer==0.12.3
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+uvicorn==0.29.0
+websockets==11.0.3