Duplicate from Amrrs/openai-whisper-live-transcribe

Co-authored-by: amrrs <[email protected]>

.gitattributes

@@ -0,0 +1,31 @@
+*.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
+*.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
+*.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
+*.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
+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
+*.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

README.md

@@ -0,0 +1,14 @@
+---
+title: Openai Whisper Live Transcribe
+emoji: 🎙
+colorFrom: yellow
+colorTo: gray
+sdk: gradio
+sdk_version: 3.3.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: Amrrs/openai-whisper-live-transcribe
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,36 @@
+import whisper
+import gradio as gr
+
+model = whisper.load_model("small")
+
+def transcribe(audio):
+    
+    #time.sleep(3)
+    # load audio and pad/trim it to fit 30 seconds
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+
+    # make log-Mel spectrogram and move to the same device as the model
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+
+    # detect the spoken language
+    _, probs = model.detect_language(mel)
+    print(f"Detected language: {max(probs, key=probs.get)}")
+
+    # decode the audio
+    options = whisper.DecodingOptions(fp16 = False)
+    result = whisper.decode(model, mel, options)
+    return result.text
+    
+    
+ 
+gr.Interface(
+    title = 'OpenAI Whisper ASR Gradio Web UI', 
+    fn=transcribe, 
+    inputs=[
+        gr.inputs.Audio(source="microphone", type="filepath")
+    ],
+    outputs=[
+        "textbox"
+    ],
+    live=True).launch()

requirements.txt

@@ -0,0 +1,2 @@
+tensorflow
+git+https://github.com/openai/whisper.git