Duplicate from antonbol/finetune_whisper

Co-authored-by: Anton Bölenius <[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: Finetune Whisper
+emoji: 🌍
+colorFrom: pink
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.12.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: antonbol/finetune_whisper
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,30 @@
+from transformers import pipeline
+import gradio as gr
+from numpy import random 
+from PIL import Image
+pipe = pipeline(model="fimster/whisper-small-sv-SE")  # change to "your-username/the-name-you-picked"
+images = ["katt", "melon", "hund", "banan"]
+image = random.choice(images)
+
+def transcribe(audio, img):
+    text = pipe(audio)["text"]
+    text = text.replace("!", "")
+    text = text.replace(".", "")
+    text = text.replace(",", "")
+    returntext = ""
+    if text.lower() != image.lower():
+        returntext = "Du svarade fel, ditt svar var: " + text + ", rätt svar var: " + image
+    else:
+        returntext = "Du hade rätt, svaret var: " + image
+    return returntext
+
+iface = gr.Interface(
+    fn=transcribe, 
+    inputs=[gr.Audio(source="microphone", type="filepath"), gr.Image("./images/" + image + ".jpeg")], 
+    outputs="text",
+    title="Whisper Small Swedish",
+    description="Demo of whisper small ASR fine tuned to swedish. Vad är det på bilden? Spela in ditt svar genom att trycka på inspelningsknappen!",
+)
+
+
+iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+tensorflow
+torch
+sentencepiece
+numpy