Update app.py

app.py

@@ -6,11 +6,11 @@ LAST_UPDATED = "06/12/2024"
 # Datos estáticos del leaderboard
 ####################################
 leaderboard_data = [
-    {'name': 'StyleTTS 2', 'STOI': 0.998, 'PESQ': 3.921, 'WER': 0.162, 'UTMOS': 2.42, 'SpeechBERT': 0, 'Logf0': 0},
-    {'name': 'Matxa-TTS', 'STOI': 0.996, 'PESQ': 3.539, 'WER': 0.179, 'UTMOS': 3.50, 'SpeechBERT': 0, 'Logf0': 0},
-    {'name': 'Matxa-TTS-multiaccent', 'STOI': 0.996, 'PESQ': 3.415, 'WER': 0.242, 'UTMOS': 2.98, 'SpeechBERT': 0, 'Logf0': 0},
-    {'name': 'StableTTS', 'STOI': 0.997, 'PESQ': 3.643, 'WER': 0.164, 'UTMOS': 2.62, 'SpeechBERT': 0.7837, 'Logf0': 0.3831},
-    {'name': 'Vits 2', 'STOI': 0, 'PESQ': 0, 'WER': 0, 'UTMOS': 3.61, 'SpeechBERT': 0, 'Logf0': 0},
+    {'name': 'StyleTTS 2', 'PESQ': 3.921, 'WER': 0.162, 'UTMOS': 2.42, 'SpeechBERT': 0, 'Logf0': 0},
+    {'name': 'Matxa-TTS', 'PESQ': 3.539, 'WER': 0.179, 'UTMOS': 3.50, 'SpeechBERT': 0, 'Logf0': 0},
+    {'name': 'Matxa-TTS-multiaccent', 'PESQ': 3.415, 'WER': 0.242, 'UTMOS': 2.98, 'SpeechBERT': 0, 'Logf0': 0},
+    {'name': 'StableTTS', 'PESQ': 3.643, 'WER': 0.164, 'UTMOS': 2.62, 'SpeechBERT': 0.7837, 'Logf0': 0.3831},
+    {'name': 'Vits 2', 'PESQ': 0, 'WER': 0, 'UTMOS': 3.61, 'SpeechBERT': 0, 'Logf0': 0},
 ]
 
 
@@ -20,7 +20,6 @@ METRICS_TAB_TEXT = """
 Models in the leaderboard are evaluated using several key metrics: 
 * **UTMOS** (UTokyo-SaruLab Mean Opinion Score),
 * **WER** (Word Error Rate),
-* **STOI** (Short-Time Objective Intelligibility),
 * **PESQ** (Perceptual Evaluation of Speech Quality).
 These metrics help evaluate both the accuracy and quality of the model.
 ### UTMOS (UTokyo-SaruLab Mean Opinion Score)[[Paper](https://arxiv.org/abs/2204.02152)]
@@ -38,8 +37,8 @@ The WER calculation is done as follows:
 ```
 WER = (S + I + D) / N = (1 + 0 + 1) / 6 = 0.333
 ```
-### STOI (Short-Time Objective Intelligibility)[[Paper](https://ieeexplore.ieee.org/abstract/document/5495701?casa_token=PLtqLc8KNAgAAAAA:FOLuZ4dgMYsnGb1dQHgqVOouQzRJ3vA5yqj-sbwf8gs9Q-AIDCLkMZzAgzRrAogwwxULK9zsYeE)]
-STOI measures the intelligibility of the synthesized speech signal compared to the original signal. **A higher STOI indicates better intelligibility**.
+Moreover, We calculate the WER using the STT_Ca_Citrinet_512 model. [[Link](https://langtech-bsc.gitbook.io/aina-kit/aina-hack/automatic-speech-recognition)]
+
 ### PESQ (Perceptual Evaluation of Speech Quality)[[Paper](https://ieeexplore.ieee.org/abstract/document/941023?casa_token=jdtHy84_KhQAAAAA:qHN3WbT6cNdufj6OOn_fn0Je0RedMv-WJCmhQ_3CWy4nMTuDvFMF3KstAmKqLx5suQwdPgGByoY)]
 PESQ is a perceptual metric that evaluates the quality of speech in a similar manner to how a human listener would. **A higher PESQ indicates better voice quality**.
 ## Benchmark Datasets
@@ -76,7 +75,7 @@ def get_leaderboard():
     for rank, model in enumerate(sorted_leaderboard):
         model['rank'] = rank + 1  # rank es la posición en la lista (1-indexed)
     
-    return [[model['rank'], model['name'], model['UTMOS'], model['WER'], model['STOI'], model['PESQ'], model['SpeechBERT'], model['Logf0']] for model in sorted_leaderboard]
+    return [[model['rank'], model['name'], model['UTMOS'], model['WER'], model['PESQ'], model['SpeechBERT'], model['Logf0']] for model in sorted_leaderboard]
 
 ####################################
 # Interfaz con Gradio
@@ -92,8 +91,8 @@ with gr.Blocks(theme=theme) as demo:
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
         with gr.TabItem("🏅 Leaderboard", elem_id="od-benchmark-tab-table", id=0):
             leaderboard_table = gr.DataFrame(
-                headers=["Rank", "Model", "UTMOS ⬆️️", "WER ⬇️", "STOI", "PESQ", "SpeechBERT ⬆️", "Logf0 ⬆️"], 
-                datatype=["str", "str", "str", "str", "str", "str", "str", "str"], 
+                headers=["Rank", "Model", "UTMOS ⬆️️", "WER ⬇️", "PESQ", "SpeechBERT ⬆️", "Logf0 ⬆️"], 
+                datatype=["str", "str", "str", "str", "str", "str", "str"], 
                 value=get_leaderboard()  # Carga los datos iniciales de la tabla
             )