Changed to a Flask app

README.md

@@ -3,7 +3,7 @@ title: Lotus
 emoji: 🪷
 colorFrom: purple
 colorTo: green
-sdk: gradio
+sdk: docker
 sdk_version: 3.39.0
 app_file: app.py
 pinned: false

app.py

@@ -1,20 +1,63 @@
-import gradio as gr
+from flask import Flask, jsonify, request
 from librosa.feature import mfcc
 import numpy as np
 from scipy.io.wavfile import read
 from tsai.all import *
+from werkzeug.utils import secure_filename
 
-tone = load_minirocket("minirocket-tone-8981")
-vowel = load_minirocket("minirocket-vowel-9814")
+app = Flask(__name__)
+UPLOAD_FOLDER = "./"
+app.config["UPLOAD_FOLDER"] = UPLOAD_FOLDER
 
-def classify(audio):
-    sr, data = audio
-    arr = data.astype(float)
-    m = mfcc(y=arr, sr=sr)
-    t = tone.predict(m).item(0)
-    v = tone.predict(m).item(0)
-    return t, v
+def preprocess(audio):
+    sr, a = audio
+    m = mfcc(y=a.astype(float), sr=sr)
+    l = []
+    for a in m:
+        l.append([])
+        flag = True
+        for b in a:
+            if abs(b) < 1e-3 and flag:
+                continue
+            else:
+                flag = False
+                l[len(l) - 1].append(b)
+    listy = []
+    for a in l.reverse():
+        listy.insert(0, [])
+        for b in a.reverse():
+            if abs(b) < 1e-3 and flag:
+                continue
+            else:
+                flag = False
+                listy[0].insert(0, b)
+    temp = []
+    for a in listy:
+        if len(a) < 236:
+            a.extend([0 for i in range(236 - len(a))])
+            temp.append(a)
+        elif len(a) > 236:
+            c = (len(a) - 236) / 2
+            temp.append(a[c : c + 236])
+        else:
+            temp.append(a)
+    m = np.array(temp)
+    return m
+    
+@app.route("/tone-vowel", methods=["POST"])
+def tone_vowel_pred():
+    if "blob" in request.files:
+        file = request.files["blob"]
+        filename = secure_filename(file.filename)
+        filepath = os.path.join(app.config["UPLOAD_FOLDER"], filename)
+        file.save(filepath)
+        audio = read(filepath)
+        m = preprocess(audio)
+        t = tone.predict(m).item(0)
+        v = vowel.predict(m).item(0)
+        return jsonify({"vowel": v, "tone": t})
 
-app = gr.Interface(fn=classify, inputs=gr.Audio(source="microphone"), outputs=["text", "text"])
-
-app.launch()
+if __name__ == "__main__":
+    tone = load_minirocket("minirocket-tone-8981")
+    vowel = load_minirocket("minirocket-vowel-9814")
+    app.run(debug=True)

requirements.txt

@@ -1,15 +1,9 @@
-aiofiles==23.1.0
-aiohttp==3.8.5
-aiosignal==1.3.1
-altair==5.0.1
 annotated-types==0.5.0
-anyio==3.7.1
 appdirs==1.4.4
 asttokens==2.2.1
-async-timeout==4.0.2
-attrs==23.1.0
 audioread==3.0.0
 backcall==0.2.0
+blinker==1.6.2
 blis==0.7.10
 catalogue==2.0.9
 certifi==2023.7.22
@@ -25,51 +19,35 @@ cymem==2.0.7
 debugpy==1.6.7.post1
 decorator==5.1.1
 Deprecated==1.2.14
-exceptiongroup==1.1.2
 executing==1.2.0
 fastai==2.7.12
-fastapi==0.101.0
 fastcore==1.5.29
 fastdownload==0.0.7
 fastprogress==1.0.3
-ffmpy==0.3.1
 filelock==3.12.2
+Flask==2.3.2
 fonttools==4.42.0
-frozenlist==1.4.0
-fsspec==2023.6.0
-gradio==3.39.0
-gradio_client==0.3.0
-h11==0.14.0
-httpcore==0.17.3
-httpx==0.24.1
-huggingface-hub==0.16.4
 idna==3.4
 imbalanced-learn==0.11.0
 ipykernel==6.25.1
 ipython==8.14.0
+itsdangerous==2.1.2
 jedi==0.19.0
 Jinja2==3.1.2
-joblib==1.3.1
-jsonschema==4.19.0
-jsonschema-specifications==2023.7.1
+joblib==1.3.2
 jupyter_client==8.3.0
 jupyter_core==5.3.1
 kiwisolver==1.4.4
 langcodes==3.3.0
 lazy_loader==0.3
 librosa==0.10.0.post2
-linkify-it-py==2.0.2
 lit==16.0.6
 llvmlite==0.40.1
-markdown-it-py==2.2.0
 MarkupSafe==2.1.3
 matplotlib==3.7.2
 matplotlib-inline==0.1.6
-mdit-py-plugins==0.3.3
-mdurl==0.1.2
 mpmath==1.3.0
 msgpack==1.0.5
-multidict==6.0.4
 murmurhash==1.0.9
 nest-asyncio==1.5.7
 networkx==3.1
@@ -86,7 +64,6 @@ 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==3.9.4
 packaging==23.1
 pandas==2.0.3
 parso==0.8.3
@@ -104,26 +81,20 @@ pure-eval==0.2.2
 pycparser==2.21
 pydantic==2.1.1
 pydantic_core==2.4.0
-pydub==0.25.1
 Pygments==2.16.1
 pyparsing==3.0.9
 python-dateutil==2.8.2
-python-multipart==0.0.6
 pyts==0.13.0
 pytz==2023.3
 PyYAML==6.0.1
-pyzmq==25.1.0
-referencing==0.30.2
+pyzmq==25.1.1
 requests==2.31.0
-rpds-py==0.9.2
 scikit-base==0.5.0
 scikit-learn==1.2.2
 scipy==1.11.1
-semantic-version==2.10.0
 six==1.16.0
 sktime==0.21.0
 smart-open==6.3.0
-sniffio==1.3.0
 soundfile==0.12.1
 soxr==0.3.5
 spacy==3.6.1
@@ -131,26 +102,21 @@ spacy-legacy==3.0.12
 spacy-loggers==1.0.4
 srsly==2.4.7
 stack-data==0.6.2
-starlette==0.27.0
 sympy==1.12
 thinc==8.1.11
 threadpoolctl==3.2.0
-toolz==0.12.0
 torch==2.0.1
 torchvision==0.15.2
 tornado==6.3.2
-tqdm==4.65.2
+tqdm==4.66.1
 traitlets==5.9.0
 triton==2.0.0
 tsai==0.3.7
 typer==0.9.0
 typing_extensions==4.7.1
 tzdata==2023.3
-uc-micro-py==1.0.2
 urllib3==2.0.4
-uvicorn==0.23.2
 wasabi==1.1.2
 wcwidth==0.2.6
-websockets==11.0.3
+Werkzeug==2.3.6
 wrapt==1.15.0
-yarl==1.9.2