Upload 35 files

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* 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
+Samples/emp2.wav filter=lfs diff=lfs merge=lfs -text
+Samples/Montreal[[:space:]]Vacation[[:space:]]Travel[[:space:]]Guide[[:space:]][[:space:]]Expedia.mp3 filter=lfs diff=lfs merge=lfs -text
+Samples/Que[[:space:]]es[[:space:]]TED[[:space:]]y[[:space:]]TEDx.mp3 filter=lfs diff=lfs merge=lfs -text
+Samples/test_mixture.wav filter=lfs diff=lfs merge=lfs -text
+Samples/Gujarati_2.wav filter=lfs diff=lfs merge=lfs -text
+Samples/Telugu_2.wav filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,31 @@
 ---
 title: Ai4bharat Indicwave2vec Models
-emoji: 📚
-colorFrom: yellow
-colorTo: blue
+emoji: ⚡
+colorFrom: pink
+colorTo: indigo
 sdk: gradio
-sdk_version: 4.1.1
+sdk_version: 4.0.2
 app_file: app.py
 pinned: false
 license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+
+
+Gujarati_2:
+
+અનુકૂલન કરવું એ અનુકૂલન થવાની સ્થિતિ છે આ તબક્કો સજીવને તેના વસવાટોમાં જીવવા અને પ્રજનન કરવા સક્ષમ બનાવે છે
+
+Gujarati_1:
+જૈન તત્વ જ્ઞાનમાં પાંચ પ્રકારના અણુવ્રતો બતાવ્યાં છે.
+
+Malayalam_1:
+അത്തരം ഏറ്റുപറയൽ അനുരഞ്ജനപ്രക്രിയയുടെ ഭാഗമാണ്
+
+Malayalam_2:
+ആൺപൂച്ചയുടെ ലിംഗത്തിൽ പിറകിലേയ്ക്ക് നിൽക്കുന്ന മുളളുകൾ ഉണ്ടാകും
+
+Malayalam_3:
+ആക്രമണമുണ്ടായ ഉടൻ ഒട്ടേറെപ്പേർ പ്രാണരക്ഷാർഥം ഏറ്റവും മുകളിലത്തെ നിലയിലേക്ക് ഓടിക്കയറി

Samples/Gujarati_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d087ac4bc15ddccecbbded4c8fdd2c9501bd8e08c6550f9c03ec46bd2df64da
+size 1597484

Samples/Montreal Vacation Travel Guide Expedia.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5148bfd0aca841584c6120c9b02c4c3d9aada2e9b015827a7869803b6471cb
+size 8058808

Samples/Que es TED y TEDx.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120a8f591bec8715dea618a14bf0538ec03444aaf875994bac0d8a1506f2ffdc
+size 1852114

Samples/Telugu_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccee4c1d338d4d6fc96dfca5f48ecac3d9b9517e44f0302037fe46304e9e76b0
+size 1122348

Samples/emp2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133ac69ac8a7d99f1fe92b7dbd810d7f4e44cd4f282179aa8c5d83183e64ad61
+size 1122066

Samples/test_mixture.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7126269f058724336d28bf6e82fa14b7030de321dbafa48c9fa20884d35dab9d
+size 1546250

app.py

@@ -0,0 +1,44 @@
+import time
+from transformers import pipeline
+import gradio as gr
+import numpy as np
+import librosa
+
+transcriber_hindi = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec-hindi")
+transcriber_bengali = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_bengali")
+transcriber_odia = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec-odia")
+transcriber_gujarati = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_gujarati")
+# transcriber_telugu = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_telugu")
+# transcriber_sinhala = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_sinhala")
+# transcriber_tamil = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_tamil")
+# transcriber_nepali = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_nepali")
+# transcriber_marathi = pipeline("automatic-speech-recognition", model="ai4bharat/indicwav2vec_v1_marathi")
+
+languages = ["hindi","bengali","odia","gujarati"]
+
+def resample_to_16k(audio, orig_sr):
+    y_resampled = librosa.resample(y=audio, orig_sr=orig_sr, target_sr=16000)
+    return y_resampled
+
+def transcribe(audio,lang="hindi"):
+    sr,y = audio
+    y = y.astype(np.float32)
+    y/= np.max(np.abs(y))
+    y_resampled = resample_to_16k(y,sr)
+    if lang not in languages:
+        return "No Model","So Stay tuned!"
+    pipe= eval(f'transcriber_{lang}')
+    start_time = time.time()
+    trans = pipe(y_resampled)
+    end_time = time.time()
+    
+    return trans["text"],(end_time-start_time)
+
+demo = gr.Interface(
+            transcribe,
+            inputs=["microphone",gr.Radio(["hindi","bengali","odia","gujarati"],value="hindi")],
+            # inputs=["microphone",gr.Radio(["hindi","bengali","odia","gujarati","telugu","sinhala","tamil","nepali","marathi"],value="hindi")],
+            outputs=["text","text"],
+            examples=[["./Samples/Hindi_1.mp3","hindi"],["./Samples/Hindi_2.mp3","hindi"],["./Samples/Hindi_3.mp3","hindi"],["./Samples/Hindi_4.mp3","hindi"],["./Samples/Hindi_5.mp3","hindi"],["./Samples/Tamil_2.mp3","hindi"],["./Samples/climate ex short.wav","hindi"],["./Samples/Gujarati_1.wav","gujarati"],["./Samples/Gujarati_2.wav","gujarati"],["./Samples/Bengali_1.wav","bengali"],["./Samples/Bengali_2.wav","bengali"]])
+            # examples=[["./Samples/Hindi_1.mp3","hindi"],["./Samples/Hindi_2.mp3","hindi"],["./Samples/Tamil_1.mp3","tamil"],["./Samples/Tamil_2.mp3","hindi"],["./Samples/Nepal_1.mp3","nepali"],["./Samples/Nepal_2.mp3","nepali"],["./Samples/Marathi_1.mp3","marathi"],["./Samples/Marathi_2.mp3","marathi"],["./Samples/climate ex short.wav","hindi"]])
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+transformers[sentencepiece]
+torch
+torchaudio
+librosa
+tensorflow