Duplicate from speechbox/whisper-restore-punctuation

Co-authored-by: Patrick von Platen <patrickvonplaten@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 +1,14 @@
+---
+title: Whisper Restore Punctuation
+emoji: 👀
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 3.15.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: speechbox/whisper-restore-punctuation
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,46 @@
+from speechbox import PunctuationRestorer
+import librosa
+import subprocess
+import gradio as gr
+
+restorer = PunctuationRestorer.from_pretrained("openai/whisper-tiny.en")
+
+
+def convert_to_wav(path):
+    if path[-3:] != 'wav':
+        new_path = '.'.join(path.split('.')[:-1]) + '.wav'
+    try:
+        subprocess.call(['ffmpeg', '-i', path, new_path, '-y'])
+    except:  # noqa: E722
+        return path, 'Error: Could not convert file to .wav'
+    path = new_path
+    return path, None
+
+
+def restore(audio, original_transcript):
+    path, error = convert_to_wav(audio)
+    print(error)
+    data, samplerate = librosa.load(path, sr=16_000)
+
+    text, log_probs = restorer(data, original_transcript, samplerate, num_beams=1)
+
+    return text, log_probs
+
+
+gr.Interface(
+    title='Punctuation Restorer',
+    fn=restore,
+    inputs=[
+        gr.inputs.Audio(source="upload", type="filepath"),
+        gr.inputs.Textbox(default="", label="normalized text")
+    ],
+    outputs=[
+        gr.outputs.Textbox(label='Restored text'),
+        gr.Number(label='Log probability')
+    ],
+    examples=[
+        ["./common_voice_en_18301577.mp3", "do not cross the yellow light"],
+        ["./sample1.flac", "going along slushy country roads and speaking to damp audiences in draughty school rooms day after day for a fortnight he'll have to put in an appearance at some place of worship on sunday morning and he can come to us immediately afterwards"],
+        ["./sample2.flac", "before he had time to answer a much encumbered vera burst into the room with the question i say can i leave these here these were a small black pig and a lusty specimen of black red game cock"],
+    ]
+  ).launch()

requirements.txt

@@ -0,0 +1,5 @@
+transformers>=4.25.0
+torch
+speechbox>=0.1.2
+librosa
+accelerate