Duplicate from mrolando/transcribe_audio

Co-authored-by: Matias Rolando <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,14 @@
+---
+title: Transcribe Audio
+emoji: 🌖
+colorFrom: indigo
+colorTo: pink
+sdk: gradio
+sdk_version: 3.40.1
+app_file: app.py
+pinned: false
+license: cc-by-nc-4.0
+duplicated_from: mrolando/transcribe_audio
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,62 @@
+from transformers import pipeline
+import base64 
+import gradio as gr
+
+model_id = "openai/whisper-medium"  # update with your model id
+#model_id ="openai/whisper-tiny"
+pipe = pipeline("automatic-speech-recognition", model=model_id)
+
+def transcribe_speech(filepath):
+    output = pipe(
+        filepath,
+        max_new_tokens=256,
+        generate_kwargs={
+            "task": "transcribe",
+            "language": "spanish",
+        },  # update with the language you've fine-tuned on
+        chunk_length_s=30,
+        batch_size=8,
+    )
+    return output["text"]
+
+
+
+
+with open("Iso_Logotipo_Ceibal.png", "rb") as image_file:
+    encoded_image = base64.b64encode(image_file.read()).decode()
+
+demo = gr.Blocks()
+
+mic_transcribe = gr.Interface(
+    fn=transcribe_speech,
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs="textbox",
+)
+
+file_transcribe = gr.Interface(
+    fn=transcribe_speech,
+    inputs=gr.Audio(source="upload", type="filepath"),
+    outputs="textbox",
+)
+
+
+with demo:
+    gr.Markdown(
+    """
+    <center>
+    <h1>
+    Uso de AI para transcribir audio a texto.
+    </h1>
+    <img src='data:image/jpg;base64,{}' width=200px>
+    <h3>
+    Con este espacio podrás transcribir audio a texto. 
+    </h3>
+    </center>
+    """.format(encoded_image))
+
+    gr.TabbedInterface(
+        [mic_transcribe, file_transcribe],
+        ["Transcribir desde el micrófono.", "Transcribir desde un Archivo de Audio."],
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers
+torch