Duplicate from radames/Speech-Recognition-Example

Co-authored-by: Radamés Ajna <radames@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.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
+*.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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar 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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+venv

README.md

@@ -0,0 +1,13 @@
+---
+title: Speech Recognition Example
+emoji: 🗣
+colorFrom: red
+colorTo: pink
+sdk: gradio
+sdk_version: 2.9.4
+app_file: app.py
+pinned: false
+duplicated_from: radames/Speech-Recognition-Example
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,23 @@
+import gradio as gr
+from transformers import pipeline
+
+
+model = pipeline(task="automatic-speech-recognition",
+                 model="facebook/s2t-medium-librispeech-asr")
+
+
+def predict_speech_to_text(audio):
+    prediction = model(audio)
+    text = prediction['text']
+    return text
+
+
+gr.Interface(fn=predict_speech_to_text,
+             title="Automatic Speech Recognition (ASR)",
+             inputs=gr.inputs.Audio(
+                 source="microphone", type="filepath", label="Input"),
+             outputs=gr.outputs.Textbox(label="Output"),
+             description="Using pipeline with Facebook S2T for ASR.",
+             examples=['ljspeech.wav'],
+             allow_flagging='never'
+             ).launch()

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,5 @@
+torch
+torchaudio
+transformers
+sentencepiece
+gradio