initial commit

app.py

@@ -0,0 +1,36 @@
+import soundfile as sf
+import torch
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import gradio as gr
+import sox
+import os
+
+def convert(inputfile, outfile):
+    sox_tfm = sox.Transformer()
+    sox_tfm.set_output_format(
+        file_type="wav", channels=1, encoding="signed-integer", rate=16000, bits=16
+    )
+    sox_tfm.build(inputfile, outfile)
+api_token = os.getenv("API_TOKEN")
+model_name = "shahukareem/Wav2Vec2-Large-XLSR-53-Dhivehi"
+processor = Wav2Vec2Processor.from_pretrained(model_name, use_auth_token=api_token)
+model = Wav2Vec2ForCTC.from_pretrained(model_name, use_auth_token=api_token)
+def parse_transcription(wav_file):
+    filename = wav_file.name.split('.')[0]
+    convert(wav_file.name, filename + "16k.wav")
+    speech, _ = sf.read(filename + "16k.wav")
+    input_values = processor(speech, sampling_rate=16_000, return_tensors="pt").input_values
+    logits = model(input_values).logits
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = processor.decode(predicted_ids[0], skip_special_tokens=True)
+    return transcription
+output = gr.outputs.Textbox(label="The transcript")
+input_ = gr.inputs.Audio(source="microphone", type="file")
+gr.Interface(parse_transcription, inputs=input_,  outputs=[output],
+             analytics_enabled=False,
+             show_tips=False,
+             theme='huggingface',
+             layout='vertical',
+             title="Speech Recognition for Dhivehi",
+             description="Speech Recognition Live Demo for Dhivehi",
+             enable_queue=True).launch( inline=False)

packages.txt

@@ -0,0 +1,2 @@
+libsndfile1
+sox

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+soundfile
+torch
+transformers
+sox
+sentencepiece