Upload 4 files

README.md

@@ -1,13 +1,13 @@
 ---
-title: Automatic Speech Recognice
-emoji: 💻
-colorFrom: blue
-colorTo: gray
+title: Automatic Speech Recognititon
+emoji: 👀
+colorFrom: indigo
+colorTo: purple
 sdk: gradio
 sdk_version: 4.29.0
 app_file: app.py
 pinned: false
-license: mit
+license: apache-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,47 @@
+from transformers import pipeline
+
+asr = pipeline(task="automatic-speech-recognition",
+               model= "distil-whisper/distil-small.en")
+
+import gradio as gr
+demo = gr.Blocks()
+
+def transcribe_long_form(filepath):
+    if filepath is None:
+        gr.Warning("No audio found, please retry")
+        return
+    output = asr(filepath,
+                 max_new_tokens=256,
+                 chunk_length_s=30,
+                 batch_size=4,)
+    return output['text']
+
+mic_transcribe = gr.Interface(
+    fn=transcribe_long_form,
+    inputs=gr.Audio(sources="microphone",
+                    type="filepath"),
+    outputs=gr.Textbox(label="Transcription",
+                       lines=7),
+    allow_flagging="never",
+    description="Speak into the microphone or upload an audio file to transcribe it into text. This model uses a state-of-the-art speech recognition algorithm to recognize spoken words and phrases")
+
+file_transcribe = gr.Interface(
+    fn=transcribe_long_form,
+    inputs=gr.Audio(sources="upload",
+                    type="filepath"),
+    outputs=gr.Textbox(label="Transcription",
+                       lines=7),
+    allow_flagging="never",
+    description="Speak into the microphone or upload an audio file to transcribe it into text. This model uses a state-of-the-art speech recognition algorithm to recognize spoken words and phrases")
+
+
+
+with demo:
+    gr.TabbedInterface(
+        [mic_transcribe,
+         file_transcribe],
+        ["Transcribe Microphone",
+         "Transcribe Audio File"],
+        title="SpeechScribe - Automatic Speech Recognition"
+    )
+demo.launch()

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

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+gradio
+soundfile
+librosa
+torch