Duplicate from JPLTedCas/TedCasSpeechRecognition

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow 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
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz 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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl 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
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,14 @@
+---
+title: TedCasSpeechRecognition
+emoji: 💩
+colorFrom: green
+colorTo: gray
+sdk: gradio
+sdk_version: 3.3.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: JPLTedCas/TedCasSpeechRecognition
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,54 @@
+from transformers import pipeline
+import gradio as gr
+import time
+
+p = pipeline("automatic-speech-recognition",model="jonatasgrosman/wav2vec2-large-xlsr-53-spanish")
+pc = pipeline("automatic-speech-recognition",model="softcatala/wav2vec2-large-xlsr-catala")
+pe = pipeline("automatic-speech-recognition",model="jonatasgrosman/wav2vec2-large-xlsr-53-english")
+pj = pipeline("automatic-speech-recognition",model="jonatasgrosman/wav2vec2-large-xlsr-53-japanese")
+pf = pipeline("automatic-speech-recognition",model="jonatasgrosman/wav2vec2-large-xlsr-53-french")
+
+
+
+
+def transcribe(language,audio, state=""):#language="Spanish",
+    time.sleep(1)
+    if language=="Spanish":
+        state=""
+        text = p(audio)["text"]
+    if language=="Catalan":
+        state=""
+        text = pc(audio)["text"]
+    if language=="English":
+        state=""
+        text = pe(audio)["text"]
+    if language=="French":
+        state=""
+        text = pf(audio)["text"]
+    if language=="Japanese":
+        state=""
+        text = pj(audio)["text"]
+    state += text + " "
+    #text2="Esto es loq ue te he entendido"
+    return state, state
+
+demo=gr.Interface(
+    fn=transcribe, 
+    
+    title="TEDCAS Offline Speech recognition",
+    description="1)Select language 2)Click on 'record from microphone' and talk 3)Click on 'stop recording' 4)Click on submit 5)Before starting again, click on 'clear'",
+
+    inputs=[
+        gr.Dropdown(["Spanish","Catalan","English", "French", "Japanese"],value="Spanish"),
+        #gr.Audio(source="microphone", type="filepath", streaming=True), 
+        gr.inputs.Audio(source="microphone", type="filepath"), 
+        "state"#,"language"
+    ],
+    outputs=[
+        "textbox",
+        "state"
+    ],
+    #live=True).launch()
+)
+demo.launch()
+#demo.launch(auth=("TedCas", "Kike1234"))

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,4 @@
+transformers
+torch
+pyctcdecode
+pypi-kenlm