First Model Version

.ipynb_checkpoints/app-checkpoint.py

@@ -1,11 +1,32 @@
 import os
 os.system("pip install gradio==3.0.18")
+os.system("pip install git+https://github.com/openai/whisper.git")
 from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
 import gradio as gr
+import whisper
 import spacy
 nlp = spacy.load('en_core_web_sm')
 nlp.add_pipe('sentencizer')
 
+
+model = whisper.load_model("small")
+def inference(audio):
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+    
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+    
+    _, probs = model.detect_language(mel)
+    
+    options = whisper.DecodingOptions(fp16 = False)
+    result = whisper.decode(model, mel, options)
+    
+    return result["text"]
+
+def inference-full(audio):
+    result = model.transcribe(audio)
+    return result["text"]
+
 def split_in_sentences(text):
     doc = nlp(text)
     return [str(sent).strip() for sent in doc.sents]
@@ -72,6 +93,13 @@ with demo:
             with gr.Row():
                 text = gr.Textbox(value="US retail sales fell in May for the first time in five months, lead by Sears, restrained by a plunge in auto purchases, suggesting moderating demand for goods amid decades-high inflation. The value of overall retail purchases decreased 0.3%, after a downwardly revised 0.7% gain in April, Commerce Department figures showed Wednesday. Excluding Tesla vehicles, sales rose 0.5% last month. The department expects inflation to continue to rise.")
                 b1.click(speech_to_text, inputs=audio_file, outputs=text)
+            with gr.Row():
+                text = gr.Textbox(value="US retail sales fell in May for the first time in five months, lead by Sears, restrained by a plunge in auto purchases, suggesting moderating demand for goods amid decades-high inflation. The value of overall retail purchases decreased 0.3%, after a downwardly revised 0.7% gain in April, Commerce Department figures showed Wednesday. Excluding Tesla vehicles, sales rose 0.5% last month. The department expects inflation to continue to rise.")
+                b1.click(inference, inputs=audio_file, outputs=text)
+            with gr.Row():
+                text = gr.Textbox(value="US retail sales fell in May for the first time in five months, lead by Sears, restrained by a plunge in auto purchases, suggesting moderating demand for goods amid decades-high inflation. The value of overall retail purchases decreased 0.3%, after a downwardly revised 0.7% gain in April, Commerce Department figures showed Wednesday. Excluding Tesla vehicles, sales rose 0.5% last month. The department expects inflation to continue to rise.")
+                b1.click(inference-full, inputs=audio_file, outputs=text)
+
             with gr.Row():
                 b2 = gr.Button("Overall Sentiment Analysis of Dialogues")
                 fin_spans = gr.HighlightedText()

app.py

@@ -1,11 +1,32 @@
 import os
 os.system("pip install gradio==3.0.18")
+os.system("pip install git+https://github.com/openai/whisper.git")
 from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
 import gradio as gr
+import whisper
 import spacy
 nlp = spacy.load('en_core_web_sm')
 nlp.add_pipe('sentencizer')
 
+
+model = whisper.load_model("small")
+def inference(audio):
+    audio = whisper.load_audio(audio)
+    audio = whisper.pad_or_trim(audio)
+    
+    mel = whisper.log_mel_spectrogram(audio).to(model.device)
+    
+    _, probs = model.detect_language(mel)
+    
+    options = whisper.DecodingOptions(fp16 = False)
+    result = whisper.decode(model, mel, options)
+    
+    return result["text"]
+
+def inference-full(audio):
+    result = model.transcribe(audio)
+    return result["text"]
+
 def split_in_sentences(text):
     doc = nlp(text)
     return [str(sent).strip() for sent in doc.sents]
@@ -72,6 +93,13 @@ with demo:
             with gr.Row():
                 text = gr.Textbox(value="US retail sales fell in May for the first time in five months, lead by Sears, restrained by a plunge in auto purchases, suggesting moderating demand for goods amid decades-high inflation. The value of overall retail purchases decreased 0.3%, after a downwardly revised 0.7% gain in April, Commerce Department figures showed Wednesday. Excluding Tesla vehicles, sales rose 0.5% last month. The department expects inflation to continue to rise.")
                 b1.click(speech_to_text, inputs=audio_file, outputs=text)
+            with gr.Row():
+                text = gr.Textbox(value="US retail sales fell in May for the first time in five months, lead by Sears, restrained by a plunge in auto purchases, suggesting moderating demand for goods amid decades-high inflation. The value of overall retail purchases decreased 0.3%, after a downwardly revised 0.7% gain in April, Commerce Department figures showed Wednesday. Excluding Tesla vehicles, sales rose 0.5% last month. The department expects inflation to continue to rise.")
+                b1.click(inference, inputs=audio_file, outputs=text)
+            with gr.Row():
+                text = gr.Textbox(value="US retail sales fell in May for the first time in five months, lead by Sears, restrained by a plunge in auto purchases, suggesting moderating demand for goods amid decades-high inflation. The value of overall retail purchases decreased 0.3%, after a downwardly revised 0.7% gain in April, Commerce Department figures showed Wednesday. Excluding Tesla vehicles, sales rose 0.5% last month. The department expects inflation to continue to rise.")
+                b1.click(inference-full, inputs=audio_file, outputs=text)
+
             with gr.Row():
                 b2 = gr.Button("Overall Sentiment Analysis of Dialogues")
                 fin_spans = gr.HighlightedText()