Duplicate from Tlanextli/Speech2Text_Ge

.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

README.md

@@ -0,0 +1,14 @@
+---
+title: Stimme2Text
+emoji: 🐢
+colorFrom: gray
+colorTo: blue
+sdk: gradio
+sdk_version: 3.42.0
+app_file: app.py
+pinned: false
+license: afl-3.0
+duplicated_from: Tlanextli/Speech2Text_Ge
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

ReverseAudio_app.py

@@ -0,0 +1,19 @@
+import os
+
+import numpy as np
+
+import gradio as gr
+
+
+def reverse_audio(audio):
+    sr, data = audio
+    return (sr, np.flipud(data))
+
+
+demo = gr.Interface(fn=reverse_audio, 
+                    inputs="microphone", 
+                    outputs="audio"
+                   )
+
+if __name__ == "__main__":
+    demo.launch()

app.py

@@ -0,0 +1,34 @@
+import os
+import gradio as gr
+from transformers import pipeline
+
+title = "Transcribe speech in German"
+
+pipeline = pipeline(task="automatic-speech-recognition", model="jonatasgrosman/wav2vec2-large-xlsr-53-german")
+#pipeline = pipeline(task="automatic-speech-recognition", model="openai/whisper-large")
+
+def transcribeFile(audio_path : str) -> str:
+    transcription = pipeline(audio_path)
+    return transcription["text"]
+
+
+app1 = gr.Interface(
+    fn=transcribeFile,
+    inputs=gr.inputs.Audio(label="Upload audio file", type="filepath"),
+    outputs="text",
+    title=title
+)
+
+
+app2 = gr.Interface(
+    fn=transcribeFile,
+    inputs=gr.Audio(source="microphone", type="filepath"), 
+    outputs="text",
+    title=title
+)
+
+
+demo = gr.TabbedInterface([app1, app2], ["Audio File", "Microphone"])
+
+if __name__ == "__main__":
+    demo.launch()

app_en.py

@@ -0,0 +1,21 @@
+import os
+import gradio as gr
+from transformers import pipeline
+
+pipeline = pipeline(task="automatic-speech-recognition", model="openai/whisper-large")
+
+def transcribe(audio_path : str) -> str:
+    transcription = pipeline(audio_path)
+    return transcription
+
+
+demo = gr.Interface(
+    fn=transcribe,
+    #inputs="microphone",
+    inputs=gr.inputs.Audio(label="Upload audio file", type="filepath"),
+    outputs="text"
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

app_ge.py

@@ -0,0 +1,22 @@
+import os
+import gradio as gr
+from transformers import pipeline
+
+pipeline = pipeline(task="automatic-speech-recognition", model="jonatasgrosman/wav2vec2-large-xlsr-53-german")
+#pipeline = pipeline(task="automatic-speech-recognition", model="openai/whisper-large")
+
+def transcribe(audio_path : str) -> str:
+    transcription = pipeline(audio_path)
+    return transcription["text"]
+
+
+demo = gr.Interface(
+    fn=transcribe,
+    #inputs="microphone",
+    inputs=gr.inputs.Audio(label="Upload audio file", type="filepath"),
+    outputs="text"
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+torch
+kenlm
+pyctcdecode
+numpy