Duplicate from Bishan/Speech_To_Text_Odia

.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 +1,13 @@
+---
+title: Speech To Text Odia
+emoji: 👁
+colorFrom: gray
+colorTo: blue
+sdk: gradio
+sdk_version: 3.39.0
+app_file: app.py
+pinned: false
+duplicated_from: Bishan/Speech_To_Text_Odia
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,76 @@
+import soundfile as sf
+import torch
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor,Wav2Vec2ProcessorWithLM
+import gradio as gr
+import sox
+import subprocess
+
+
+def read_file_and_process(wav_file):
+    filename = wav_file.split('.')[0]
+    filename_16k = filename + "16k.wav"
+    resampler(wav_file, filename_16k)
+    speech, _ = sf.read(filename_16k)
+    inputs = processor(speech, sampling_rate=16_000, return_tensors="pt", padding=True)
+    
+    return inputs
+
+
+def resampler(input_file_path, output_file_path):
+    command = (
+        f"ffmpeg -hide_banner -loglevel panic -i {input_file_path} -ar 16000 -ac 1 -bits_per_raw_sample 16 -vn "
+        f"{output_file_path}"
+    )
+    subprocess.call(command, shell=True)
+
+
+def parse_transcription_with_lm(logits):
+    result = processor_with_LM.batch_decode(logits.cpu().numpy())
+    text = result.text
+    transcription = text[0].replace('<s>','')
+    return transcription
+
+def parse_transcription(logits):
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = processor.decode(predicted_ids[0], skip_special_tokens=True)
+    return transcription
+
+def parse(wav_file, applyLM):
+    input_values = read_file_and_process(wav_file)
+    with torch.no_grad():
+        logits = model(**input_values).logits
+   
+    if applyLM:
+        return parse_transcription_with_lm(logits)
+    else:
+        return parse_transcription(logits)
+
+
+# processor = Wav2Vec2Processor.from_pretrained("Harveenchadha/vakyansh-wav2vec2-odia-orm-100")
+# processor_with_LM = Wav2Vec2ProcessorWithLM.from_pretrained("Harveenchadha/vakyansh-wav2vec2-odia-orm-100")
+# model = Wav2Vec2ForCTC.from_pretrained("Harveenchadha/vakyansh-wav2vec2-odia-orm-100")
+
+
+processor = Wav2Vec2Processor.from_pretrained("Harveenchadha/odia_large_wav2vec2")
+processor_with_LM = Wav2Vec2ProcessorWithLM.from_pretrained("Harveenchadha/odia_large_wav2vec2")
+model = Wav2Vec2ForCTC.from_pretrained("Harveenchadha/odia_large_wav2vec2")
+
+
+# processor = Wav2Vec2Processor.from_pretrained("theainerd/wav2vec2-large-xlsr-53-odia")
+# processor_with_LM = Wav2Vec2ProcessorWithLM.from_pretrained("theainerd/wav2vec2-large-xlsr-53-odia")
+# model = Wav2Vec2ForCTC.from_pretrained("theainerd/wav2vec2-large-xlsr-53-odia")
+
+
+
+    
+input_ = gr.Audio(source="upload", type="filepath")  
+txtbox = gr.Textbox(
+            label="Output from model will appear here:",
+            lines=5
+        )
+chkbox = gr.Checkbox(label="Apply LM", value=False)
+
+
+gr.Interface(parse, inputs = [input_, chkbox],  outputs=txtbox,
+             streaming=True, interactive=True,
+             analytics_enabled=False, show_tips=False, enable_queue=True).launch(inline=False);

packages.txt

@@ -0,0 +1,4 @@
+libsndfile1
+sox
+ffmpeg
+

requirements.txt

@@ -0,0 +1,8 @@
+gradio
+https://github.com/kpu/kenlm/archive/master.zip
+pyctcdecode
+soundfile
+torch
+transformers
+sox
+scipy