save

.gitattributes

@@ -2,13 +2,11 @@
 *.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
@@ -16,13 +14,12 @@
 *.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
+*.pb 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
 *.tflite filter=lfs diff=lfs merge=lfs -text
@@ -31,4 +28,4 @@ saved_model/**/* 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
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,12 @@
 ---
-title: Hf Openai Whisper Dev
-emoji: 🏃
-colorFrom: indigo
-colorTo: red
+title: V-to-text (dev)
+emoji: 🗣
+colorFrom: pink
+colorTo: yellow
 sdk: gradio
-sdk_version: 3.27.0
+sdk_version: 3.3.1
 app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,96 @@
+import os
+os.system("pip install git+https://github.com/openai/whisper.git")
+import gradio as gr
+import whisper
+from flask import Flask, jsonify, request
+import requests
+import streamlit as st
+import time
+
+
+model = whisper.load_model("large-v2")
+
+app = Flask(__name__)
+
+@app.route("/")
+def indexApi():
+    return jsonify({"output": "okay"})
+
+@app.route("/run", methods=['POST'])
+def runApi():
+    start_time = time.time()
+
+    audio_url = request.form.get("audio_url")
+    # key = request.form.get("key")
+    # modelSelection = request.form.get("model")
+    # print(audio_url)
+
+    # if (modelSelection == None):
+    #     modelSelection = "small"
+    # model = whisper.load_model(modelSelection)
+    # print(model)
+
+    # # reject if key not the same 
+    # apiKey = st.secrets["Api-Key"]
+    # if apiKey != key:
+    #     return jsonify({
+    #         "image_url": image_url,
+    #         "model": model,
+    #         "result": "Invalid API Key",
+    #     }), 400
+
+
+    response = requests.get(audio_url)
+
+    if response.status_code == requests.codes.ok:
+        with open("audio.mp3", "wb") as f:
+            f.write(response.content)
+      
+    else:
+        return jsonify({
+            "result": "Unable to save file, status code:  {response.status_code}" ,
+        }), 400
+
+    # arr = np.asarray(bytearray(response.content), dtype=np.uint8)
+    # result = model.transcribe("audio.mp3")
+    audio = "audio.mp3"
+
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+    
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+    
+    _, probs = model.detect_language(mel)
+    
+    options = whisper.DecodingOptions(fp16 = False)
+    result = whisper.decode(model, mel, options)
+
+
+    end_time = time.time()
+    total_time = end_time - start_time
+
+    return jsonify({
+        "audio_url": audio_url,
+        # "model": model,
+        "result": result.text,
+        "exec_time_sec": total_time
+    })
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=7860)
+        
+# def inference(audio):
+#     audio = whisper.load_audio(audio)
+#     audio = whisper.pad_or_trim(audio)
+    
+#     mel = whisper.log_mel_spectrogram(audio).to(model.device)
+    
+#     _, probs = model.detect_language(mel)
+    
+#     options = whisper.DecodingOptions(fp16 = False)
+#     result = whisper.decode(model, mel, options)
+    
+#     # print(result.text)
+#     return result.text, gr.update(visible=True), gr.update(visible=True), gr.update(visible=True)
+
+

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+requests
+streamlit
+flask

save.sh

@@ -0,0 +1,3 @@
+git add .
+git commit -m "save"
+git push origin main