Duplicate from SteveDigital/free-mp3-to-text-using-openai-whisper

Co-authored-by: Steve Digital <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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: Free MP3-to-Text Using Openai Whisper (Works)
+emoji: 👁
+colorFrom: green
+colorTo: green
+sdk: gradio
+sdk_version: 3.16.1
+app_file: app.py
+pinned: false
+license: gpl-3.0
+duplicated_from: SteveDigital/free-mp3-to-text-using-openai-whisper
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+import whisper
+
+# duplicate this space to run on higher CPU power for the large (very precise and multi-lingual) model to work best
+ 
+def speech_to_text(uploaded, model_size):
+    model = whisper.load_model(model_size)
+    source = uploaded if uploaded is not None else ''
+    result = model.transcribe(source)
+    return f'{result["text"]}'
+
+gr.Interface(
+    title="",
+    thumbnail="",
+    css="""
+    footer {visibility: xhidden}
+    .gr-prose p{text-align: center;}
+    .gr-button {background: black;color: white}
+    """,
+    description="",
+    fn=speech_to_text,
+    inputs=[
+        gr.Audio(source="upload", type="filepath", label="Upload Audio"), 
+        gr.Dropdown(label="Select model size",value="large",choices=["tiny", "base", "small", "medium", "large"])],
+    outputs="text").launch(debug = True)

requirements.txt

@@ -0,0 +1,3 @@
+git+https://github.com/openai/whisper.git
+git+https://github.com/huggingface/transformers
+pytube