From 2c372c0aa6ffe871223a0663c0e9e3f1830c3fe0 Mon Sep 17 00:00:00 2001
From: harshit katyal <hkatyal345@gmail.com>
Date: Sun, 12 Dec 2021 20:43:57 +0000
Subject: [PATCH] Update README.md

---
 README.md | 75 ++++++++++++++++++++-----------------------------------
 1 file changed, 27 insertions(+), 48 deletions(-)

diff --git a/README.md b/README.md
index 5a3c225..8c4abef 100644
--- a/README.md
+++ b/README.md
@@ -1,25 +1,24 @@
 ---
 language: en
-datasets: Toronto emotional speech set (TESS)(https://www.kaggle.com/ejlok1/toronto-emotional-speech-set-tess)
+datasets:
+- aesdd
 tags:
 - audio
-- automatic-speech-recognition
+- audio-classification
 - speech
-- speech-emotion-recognition
 license: apache-2.0
 ---
-# Emotion Recognition in Speech using Wav2Vec 2.0
-## How to use
-### Requirements
-```bash
+~~~
 # requirement packages
 !pip install git+https://github.com/huggingface/datasets.git
 !pip install git+https://github.com/huggingface/transformers.git
 !pip install torchaudio
 !pip install librosa
-```
-### Prediction
-```python
+!git clone https://github.com/m3hrdadfi/soxan
+cd soxan
+~~~
+# prediction
+~~~
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -29,16 +28,16 @@ import librosa
 import IPython.display as ipd
 import numpy as np
 import pandas as pd
-```
-```python
+~~~
+~~~
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model_name_or_path = "harshit345/xlsr-wav2vec-speech-emotion-recognition"
+model_name_or_path = "Bagus/wav2vec2-xlsr-greek-speech-emotion-recognition"
 config = AutoConfig.from_pretrained(model_name_or_path)
 feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name_or_path)
 sampling_rate = feature_extractor.sampling_rate
 model = Wav2Vec2ForSpeechClassification.from_pretrained(model_name_or_path).to(device)
-```
-```python
+~~~
+~~~
 def speech_file_to_array_fn(path, sampling_rate):
     speech_array, _sampling_rate = torchaudio.load(path)
     resampler = torchaudio.transforms.Resample(_sampling_rate)
@@ -53,37 +52,17 @@ def predict(path, sampling_rate):
     scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
     outputs = [{"Emotion": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in enumerate(scores)]
     return outputs
-```
-```python
-path = "/path/to/disgust.wav"
+~~~
+# prediction
+~~~
+# path for a sample
+path = '/data/jtes_v1.1/wav/f01/ang/f01_ang_01.wav'   
 outputs = predict(path, sampling_rate)
-```
-```bash
-[
-{'Emotion': 'anger', 'Score': '12.2%'},
-{'Emotion': 'disgust', 'Score': '78.8%'},
-{'Emotion': 'fear', 'Score': '7.2%'},
-{'Emotion': 'happiness', 'Score': '1.3%'},
-{'Emotion': 'sadness', 'Score': '1.5%'}
-]
-```
-
-
-## Evaluation
-The following tables summarize the scores obtained by model overall and per each class.
-
-
-| Emotions  | precision | recall | f1-score | accuracy |
-|-----------|-----------|--------|----------|----------|
-| anger     | 0.82      | 1.00   | 0.81     |          |
-| disgust   | 0.85      | 0.96   | 0.85     |          |
-| fear      | 0.78      | 0.88   | 0.80     |          |
-| happiness | 0.84      | 0.71   | 0.78     |          |
-| sadness   | 0.86      | 1.00   | 0.79     |          |
-|           |           |        | Overall  | 0.806    |
-
-
-## 
-
-Colab Notebook
-https://colab.research.google.com/drive/1aPPb_ZVS5dlFVZySly8Q80a44La1XjJu?usp=sharing
\ No newline at end of file
+~~~
+~~~
+[{'Emotion': 'anger', 'Score': '98.3%'},
+ {'Emotion': 'disgust', 'Score': '0.0%'},
+ {'Emotion': 'fear', 'Score': '0.4%'},
+ {'Emotion': 'happiness', 'Score': '0.7%'},
+ {'Emotion': 'sadness', 'Score': '0.5%'}]
+ ~~~
\ No newline at end of file