Duplicate from sanchit-gandhi/whisper-small-sv-bm

Co-authored-by: Sanchit Gandhi <sanchit-gandhi@users.noreply.huggingface.co>

.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 +1,13 @@
+---
+title: Whisper Small Sv Bm
+emoji: 🇸🇪
+colorFrom: yellow
+colorTo: purple
+sdk: gradio
+sdk_version: 3.9.1
+app_file: app.py
+pinned: false
+duplicated_from: sanchit-gandhi/whisper-small-sv-bm
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+from transformers import pipeline
+import torch
+import librosa
+import soundfile
+
+SAMPLE_RATE = 16000
+
+pipe = pipeline(model="birgermoell/whisper-small-sv-bm")  # change to "your-username/the-name-you-picked"
+
+
+def process_audio_file(file):
+    data, sr = librosa.load(file)
+
+    if sr != SAMPLE_RATE:
+        data = librosa.resample(data, sr, SAMPLE_RATE)
+
+    # monochannel
+    data = librosa.to_mono(data)
+    return data
+
+
+def transcribe(Microphone, File_Upload):
+    warn_output = ""
+    if (Microphone is not None) and (File_Upload is not None):
+        warn_output = "WARNING: You've uploaded an audio file and used the microphone. " \
+                      "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
+        file = Microphone
+
+    elif (Microphone is None) and (File_Upload is None):
+        return "ERROR: You have to either use the microphone or upload an audio file"
+
+    elif Microphone is not None:
+        file = Microphone
+    else:
+        file = File_Upload
+
+    audio_data = process_audio_file(file)
+    
+    text = pipe(audio_data)["text"]
+
+    return warn_output + text
+
+
+iface = gr.Interface(
+    fn=transcribe,
+    inputs=[
+        gr.inputs.Audio(source="microphone", type='filepath', optional=True),
+        gr.inputs.Audio(source="upload", type='filepath', optional=True),
+    ],
+    outputs="text",
+    layout="horizontal",
+    theme="huggingface",
+    title="Whisper Small SV",
+    description="Demo for Swedish speech recognition using the [Whisper Small SV BM checkpoint](https://huggingface.co/birgermoell/whisper-small-sv-bm).",
+    allow_flagging='never',
+)
+
+iface.launch(enable_queue=True)

packages.txt

@@ -0,0 +1,2 @@
+ffmpeg
+libsndfile1

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+soundfile
+torch
+librosa