add app files

.gitattributes

@@ -1,35 +1,10 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+audio/plain_03.wav filter=lfs diff=lfs merge=lfs -text
+audio/plain_04.wav filter=lfs diff=lfs merge=lfs -text
+audio/plain_05.wav filter=lfs diff=lfs merge=lfs -text
+audio/secret_01.wav filter=lfs diff=lfs merge=lfs -text
+audio/secret_02.wav filter=lfs diff=lfs merge=lfs -text
+audio/plain_02.wav filter=lfs diff=lfs merge=lfs -text
+audio/plain_04b.wav filter=lfs diff=lfs merge=lfs -text
+audio/secret_03.wav filter=lfs diff=lfs merge=lfs -text
+audio/secret_04.wav filter=lfs diff=lfs merge=lfs -text
+audio/plain_01.wav filter=lfs diff=lfs merge=lfs -text

.github/workflows/deploy-hf.yml

@@ -0,0 +1,25 @@
+name: Deploy to Hugging Face spaces
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Dev Repo
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+
+      - name: Push to HF
+        env:
+          HFTOKEN: ${{ secrets.HFTOKEN }}
+
+        run: |
+          git remote add hf https://thiagohersan:$HFTOKEN@huggingface.co/spaces/visualizedata/5020-STT-Gradio
+          git push hf main

.gitignore

@@ -0,0 +1,3 @@
+.DS_S*
+__pycache__/
+gradio_cached_examples/

README.md

@@ -1,12 +1,11 @@
 ---
-title: 5020 STT Gradio
-emoji: 🦀
-colorFrom: green
-colorTo: pink
+title: 5020 whisper-base-en Speech-to-Text
+emoji: 🔊
+colorFrom: indigo
+colorTo: yellow
 sdk: gradio
-sdk_version: 5.46.1
+python_version: 3.10.12
+sdk_version: 5.0.2
 app_file: app.py
 pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+import numpy as np
+
+from librosa import resample
+from transformers import pipeline
+
+pipe = pipeline("automatic-speech-recognition", model="openai/whisper-base.en", chunk_length_s=30)
+
+def transcribe(audio_in):
+  orig_sr, samples = audio_in
+  min_s, max_s = min(samples), max(samples)
+  range_in = (max_s - min_s)
+  samples_scl = np.array(samples) / range_in
+  min_scl = min_s / range_in
+  samples_f = 2.0 * (samples_scl - min_scl) - 1.0
+  resamples = resample(samples_f, orig_sr=orig_sr, target_sr=16000)
+  prediction = pipe(resamples.copy(), batch_size=8)
+  return prediction["text"].strip().lower()
+
+
+with gr.Blocks() as demo:
+  gr.Markdown("""
+              # 5020 Audio Transcription.
+              ## API for [whisper-base.en](https://huggingface.co/openai/whisper-base.en) english model\
+              to help with Audio Analysis exercises.
+              """)
+
+  gr.Interface(
+    transcribe,
+    inputs=gr.Audio(type="numpy"),
+    outputs="text",
+    cache_examples=True,
+    examples=[["./audio/plain_01.wav"]]
+  )
+
+if __name__ == "__main__":
+   demo.launch()

audio/plain_01.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4db5391e8429e21d7c19f05c6d551e01fe168186c91d1debb055c0305e8f84f
+size 176440

audio/plain_02.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4222969e675d59440f5fec9dc7dd1fa83f4901a5b370f4fb116cdced83bfdc4f
+size 453704

audio/plain_03.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58b18ff12c5ab02b3886669aebe0dfa2181006f65b8c7ae271bea60cdc0c9f19
+size 308740

audio/plain_04.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6165df34e92ab966590fe5bd33b5afdae568ed2d26726bbaea142622805d0445
+size 439442

audio/plain_04b.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72aad56c76fa0e1e3d0c16dd41bfbf62ecc406ed216711c16b9b2b852464b1be
+size 5974316

audio/plain_05.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64aa9b09942a77e68820468e91af7ba00008ed520c03db90dad36292048feb31
+size 441040

audio/secret_01.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76b42a98c06aaeb1ac65ea7cf50063a76708d4e52466dc59684eab677857ae1
+size 176440

audio/secret_02.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be2e88e04a8a28b8bcb848a7c5a08f50fb5835ad0b1e5436d03eac18e16ef656
+size 453704

audio/secret_03.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0555b2ef8e1c29c24cd31eb622c146d028dba3b3bc0bab5467e3325d5811d769
+size 308740

audio/secret_04.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd460839bcd94d5f51f2b641fa6b557561525ecdf04ab9c18e157d8bdf99b9f8
+size 5712216

requirements.txt

@@ -0,0 +1,4 @@
+pydantic==2.8.2
+librosa
+torch
+transformers