Initial commit

README.md

@@ -1,7 +1,7 @@
 ---
-title: Finnish Asr
+title: Finnish ASR
 emoji: 🏆
-colorFrom: green
+colorFrom: red
 colorTo: indigo
 sdk: gradio
 sdk_version: 5.23.3

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+from transformers import pipeline
+from librosa import resample
+import numpy as np
+
+def transcribe(input_audio, model_id):
+    pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model_id,
+    device="cpu"
+    )
+    sr, speech = input_audio
+    # Convert to mono if stereo
+    if speech.ndim > 1:
+        speech = speech.mean(axis=1)
+    # Convert to float32 if needed
+    if speech.dtype != "float32":
+        speech = speech.astype(np.float32)
+    # Resample if sampling rate is not 16kHz
+    if sr!=16000:
+        speech = resample(speech, orig_sr=sr, target_sr=16000)
+    output = pipe(speech, chunk_length_s=30, stride_length_s=5)['text']
+    return output
+
+model_ids_list = [
+ "GetmanY1/wav2vec2-base-fi-150k-finetuned",
+ "GetmanY1/wav2vec2-large-fi-150k-finetuned",
+ "GetmanY1/wav2vec2-xlarge-fi-150k-finetuned"
+]
+
+gradio_app = gr.Interface(
+    fn=transcribe,
+    inputs=[gr.Audio(sources=["upload","microphone"]), gr.Dropdown(model_ids_list)],
+    outputs="text",
+    title="Finnish Automatic Speech Recognition"
+    description ="Choose a model from the list. Select the Base model for the fastest inference and the XLarge one for the most accurate results."
+)
+
+if __name__ == "__main__":
+    gradio_app.launch()
+
+
+
+# if __name__ == "__main__":
+#     gradio_app.launch()

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+torch
+librosa
+samplerate
+resampy