setup whisper base fa

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.11" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/najva.iml" filepath="$PROJECT_DIR$/.idea/najva.iml" />
+    </modules>
+  </component>
+</project>

.idea/najva.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

main.py

@@ -0,0 +1,41 @@
+import gradio as gr
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+import librosa
+
+processor = WhisperProcessor.from_pretrained("Neurai/NeuraSpeech_WhisperBase")
+model = WhisperForConditionalGeneration.from_pretrained("Neurai/NeuraSpeech_WhisperBase")
+forced_decoder_ids = processor.get_decoder_prompt_ids(language="fa", task="transcribe")
+
+
+def reverse_audio(audio):
+    array, sample_rate = audio
+    sr = 16000
+    array = librosa.to_mono(array)
+    array = librosa.resample(array, orig_sr=sample_rate, target_sr=16000)
+    input_features = processor(array, sampling_rate=sr, return_tensors="pt").input_features
+
+    # generate token ids
+    predicted_ids = model.generate(input_features)
+    # decode token ids to text
+    transcription = processor.batch_decode(predicted_ids, )
+    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+    return transcription
+
+
+input_audio = gr.Audio(
+    sources=["microphone"],
+    waveform_options=gr.WaveformOptions(
+        waveform_color="#01C6FF",
+        waveform_progress_color="#0066B4",
+        skip_length=2,
+        show_controls=True,
+    ),
+)
+demo = gr.Interface(
+    fn=reverse_audio,
+    inputs=input_audio,
+    outputs="text"
+)
+
+if __name__ == "__main__":
+    demo.launch()