Duplicate from DrishtiSharma/ASR_using_Wav2Vec2

Co-authored-by: Drishti Sharma <DrishtiSharma@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+title: ASR using Wav2Vec 2.0
+emoji: 🌖
+colorFrom: yellow
+colorTo: green
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: DrishtiSharma/ASR_using_Wav2Vec2
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,67 @@
+#References: 1. https://www.kdnuggets.com/2021/03/speech-text-wav2vec.html 
+            #2. https://www.youtube.com/watch?v=4CoVcsxZphE 
+            #3. https://www.analyticsvidhya.com/blog/2021/02/hugging-face-introduces-the-first-automatic-speech-recognition-model-wav2vec2/ 
+
+#Importing all the necessary packages
+import nltk
+import librosa
+import torch
+import gradio as gr
+from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForCTC
+nltk.download("punkt")
+
+#Loading the model and the tokenizer
+model_name = "facebook/wav2vec2-base-960h"
+tokenizer = Wav2Vec2Tokenizer.from_pretrained(model_name)
+model = Wav2Vec2ForCTC.from_pretrained(model_name)
+
+
+def load_data(input_file):
+  
+  """ Function for resampling to ensure that the speech input is sampled at 16KHz.
+  """
+  #read the file
+  speech, sample_rate = librosa.load(input_file)
+  #make it 1-D
+  if len(speech.shape) > 1: 
+      speech = speech[:,0] + speech[:,1]
+  #Resampling at 16KHz since wav2vec2-base-960h is pretrained and fine-tuned on speech audio sampled at 16 KHz.
+  if sample_rate !=16000:
+    speech = librosa.resample(speech, sample_rate,16000)
+  return speech
+  
+  
+
+def correct_casing(input_sentence):
+  """ This function is for correcting the casing of the generated transcribed text
+  """
+  sentences = nltk.sent_tokenize(input_sentence)
+  return (' '.join([s.replace(s[0],s[0].capitalize(),1) for s in sentences]))
+  
+
+
+def asr_transcript(input_file):
+  """This function generates transcripts for the provided audio input
+  """
+  speech = load_data(input_file)
+  
+  #Tokenize
+  input_values = tokenizer(speech, return_tensors="pt").input_values
+  #Take logits
+  logits = model(input_values).logits
+  #Take argmax
+  predicted_ids = torch.argmax(logits, dim=-1)
+  #Get the words from predicted word ids
+  transcription = tokenizer.decode(predicted_ids[0])
+  #Output is all upper case
+  transcription = correct_casing(transcription.lower())
+  return transcription
+  
+
+gr.Interface(asr_transcript,
+             inputs = gr.inputs.Audio(source="microphone", type="filepath", optional=True, label="Please record your voice"),
+             outputs = gr.outputs.Textbox(label="Output Text"),
+             title="ASR using Wav2Vec 2.0",
+             description = "This application displays transcribed text for given audio input",
+             examples = [["Test_File1.wav"], ["Test_File2.wav"], ["Test_File3.wav"]], theme="grass").launch()
+

requirements.txt

@@ -0,0 +1,4 @@
+nltk
+transformers
+torch
+librosa