Spaces:
Running
Running
Demosthene-OR
commited on
Commit
•
711ffac
1
Parent(s):
571403a
....
Browse files- .gitignore +3 -0
- __pycache__/config.cpython-310.pyc +0 -0
- __pycache__/member.cpython-310.pyc +0 -0
- __pycache__/translate_app.cpython-310.pyc +0 -0
- enregistrement.wav +0 -0
- requirements.txt +5 -2
- tabs/__pycache__/chatbot_tab.cpython-310.pyc +0 -0
- tabs/__pycache__/custom_vectorizer.cpython-310.pyc +0 -0
- tabs/__pycache__/intro.cpython-310.pyc +0 -0
- tabs/__pycache__/sentence_similarity_tab.cpython-310.pyc +0 -0
- tabs/__pycache__/speech2text_tab.cpython-310.pyc +0 -0
- tabs/chatbot_tab.py +183 -57
- tabs/intro.py +1 -0
- tabs/sentence_similarity_tab.py +1 -1
- tabs/speech2text_tab.py +0 -389
.gitignore
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
# DotEnv configuration
|
2 |
+
.env
|
3 |
+
|
__pycache__/config.cpython-310.pyc
ADDED
Binary file (530 Bytes). View file
|
|
__pycache__/member.cpython-310.pyc
ADDED
Binary file (1.25 kB). View file
|
|
__pycache__/translate_app.cpython-310.pyc
ADDED
Binary file (818 Bytes). View file
|
|
enregistrement.wav
ADDED
Binary file (706 kB). View file
|
|
requirements.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
streamlit==1.
|
2 |
pandas==2.2.1
|
3 |
matplotlib==3.8.2
|
4 |
ipython==8.21.0
|
@@ -7,7 +7,6 @@ seaborn==0.13.2
|
|
7 |
nltk==3.8.1
|
8 |
scikit-learn==1.1.3
|
9 |
scipy==1.9.3
|
10 |
-
gensim==4.3.2
|
11 |
sacrebleu==2.4.0
|
12 |
pillow==9.5.0
|
13 |
wordcloud==1.9.3
|
@@ -37,3 +36,7 @@ langchain_mistralai==0.2.0
|
|
37 |
langgraph==0.2.34
|
38 |
langsmith==0.1.131
|
39 |
typing_extensions==4.12.2
|
|
|
|
|
|
|
|
|
|
1 |
+
streamlit==1.34.0
|
2 |
pandas==2.2.1
|
3 |
matplotlib==3.8.2
|
4 |
ipython==8.21.0
|
|
|
7 |
nltk==3.8.1
|
8 |
scikit-learn==1.1.3
|
9 |
scipy==1.9.3
|
|
|
10 |
sacrebleu==2.4.0
|
11 |
pillow==9.5.0
|
12 |
wordcloud==1.9.3
|
|
|
36 |
langgraph==0.2.34
|
37 |
langsmith==0.1.131
|
38 |
typing_extensions==4.12.2
|
39 |
+
python-dotenv==1.0.1
|
40 |
+
soundfile==0.12.1
|
41 |
+
SpeechRecognition==3.10.4
|
42 |
+
sounddevice==0.5.0
|
tabs/__pycache__/chatbot_tab.cpython-310.pyc
ADDED
Binary file (8.36 kB). View file
|
|
tabs/__pycache__/custom_vectorizer.cpython-310.pyc
ADDED
Binary file (515 Bytes). View file
|
|
tabs/__pycache__/intro.cpython-310.pyc
ADDED
Binary file (949 Bytes). View file
|
|
tabs/__pycache__/sentence_similarity_tab.cpython-310.pyc
ADDED
Binary file (1.63 kB). View file
|
|
tabs/__pycache__/speech2text_tab.cpython-310.pyc
ADDED
Binary file (682 Bytes). View file
|
|
tabs/chatbot_tab.py
CHANGED
@@ -1,6 +1,16 @@
|
|
1 |
import streamlit as st # type: ignore
|
2 |
import os
|
3 |
from datetime import datetime
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
from sentence_transformers import SentenceTransformer
|
5 |
from translate_app import tr
|
6 |
import getpass
|
@@ -12,6 +22,7 @@ from typing import Sequence
|
|
12 |
from langchain_core.messages import BaseMessage, SystemMessage, HumanMessage, AIMessage, trim_messages
|
13 |
from langgraph.graph.message import add_messages
|
14 |
from typing_extensions import Annotated, TypedDict
|
|
|
15 |
|
16 |
import warnings
|
17 |
warnings.filterwarnings('ignore')
|
@@ -24,27 +35,23 @@ os.environ["LANGCHAIN_TRACING_V2"] = "true"
|
|
24 |
os.environ["LANGCHAIN_ENDPOINT"]="https://api.smith.langchain.com"
|
25 |
os.environ["LANGCHAIN_HUB_API_URL"]="https://api.smith.langchain.com"
|
26 |
os.environ["LANGCHAIN_PROJECT"] = "Sales Coaching Chatbot"
|
|
|
|
|
27 |
os.getenv("LANGCHAIN_API_KEY")
|
28 |
os.getenv("MISTRAL_API_KEY")
|
|
|
|
|
|
|
|
|
29 |
model = ChatMistralAI(model="mistral-large-latest")
|
30 |
-
thread_id = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
31 |
-
|
32 |
-
dataPath = st.session_state.DataPath
|
33 |
|
34 |
-
trimmer = trim_messages(
|
35 |
-
max_tokens=10000,
|
36 |
-
strategy="last",
|
37 |
-
token_counter=model,
|
38 |
-
include_system=True,
|
39 |
-
allow_partial=False,
|
40 |
-
start_on="human",
|
41 |
-
)
|
42 |
|
|
|
43 |
prompt = ChatPromptTemplate.from_messages(
|
44 |
[
|
45 |
(
|
46 |
"system",
|
47 |
-
"
|
48 |
),
|
49 |
MessagesPlaceholder(variable_name="messages"),
|
50 |
]
|
@@ -56,10 +63,7 @@ class State(TypedDict):
|
|
56 |
|
57 |
def call_model(state: State):
|
58 |
chain = prompt | model
|
59 |
-
|
60 |
-
response = chain.invoke(
|
61 |
-
{"messages": trimmed_messages, "language": state["language"]}
|
62 |
-
)
|
63 |
return {"messages": [response]}
|
64 |
|
65 |
# Define a new graph
|
@@ -74,14 +78,15 @@ workflow.add_edge("model", END)
|
|
74 |
memory = MemorySaver()
|
75 |
app = workflow.compile(checkpointer=memory)
|
76 |
|
77 |
-
@st.cache_data
|
78 |
def init():
|
79 |
-
global config,context,human_message1,ai_message1,
|
80 |
|
|
|
81 |
config = {"configurable": {"thread_id": thread_id}}
|
82 |
|
83 |
-
context = """Tu es un Directeur Commercial, mal organisé, d'une entreprise qui commercialise une solution technologique B2B"""
|
84 |
-
human_message1 = """Je souhaites que
|
85 |
Mon entreprise propose une solution logicielle pour gérer la proposition de valeur d’entreprises B2B qui commercialises des solutions technologiques.
|
86 |
|
87 |
Les problématiques adressées par ma solution sont:
|
@@ -114,56 +119,177 @@ et mon équipe de vente n'est pas performante.
|
|
114 |
|
115 |
Attention: Ce n'est pas toi qui m'aide, c'est moi qui t'aide avec ma solution.
|
116 |
"""
|
117 |
-
ai_message1 = "J'ai bien compris, je suis un Directeur Commercial prospecté et je réponds à
|
118 |
|
|
|
|
|
119 |
messages = [
|
120 |
SystemMessage(content=context),
|
121 |
HumanMessage(content=human_message1),
|
122 |
AIMessage(content=ai_message1),
|
|
|
123 |
]
|
124 |
|
125 |
|
126 |
-
trimmer.invoke(messages)
|
127 |
-
language = "French"
|
128 |
-
st.write("Contexte: "+context+"\n")
|
129 |
-
st.write("Human Message: "+human_message1+"\n")
|
130 |
-
st.write("AI Message: "+ai_message1+"\n")
|
131 |
-
|
132 |
-
init()
|
133 |
-
|
134 |
-
def run():
|
135 |
|
136 |
-
|
137 |
-
|
138 |
-
st.title(tr(title))
|
139 |
-
|
140 |
-
st.write("thread_id: "+thread_id)
|
141 |
-
query = st.text_area(label=tr("Vendeur:"), value="")
|
142 |
-
st.button(label=tr("Validez"), type="primary")
|
143 |
-
|
144 |
-
input_messages = [HumanMessage(query)]
|
145 |
-
if query != "":
|
146 |
-
output = app.invoke(
|
147 |
-
{"messages": input_messages, "language": language},
|
148 |
config,
|
149 |
)
|
150 |
-
st.write(output["messages"][-1].content)
|
151 |
-
|
152 |
-
|
153 |
'''
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
|
159 |
-
config,
|
160 |
-
stream_mode="messages",
|
161 |
-
):
|
162 |
-
if isinstance(chunk, AIMessage): # Filter to just model responses
|
163 |
-
# st.markdown("<span style='white-space: nowrap;'>"+"/"+chunk.content+"/"+"</span>", unsafe_allow_html=True)
|
164 |
-
placeholder.markdown(f"<p style='display: inline;'>{chunk.content}</p>", unsafe_allow_html=True)
|
165 |
'''
|
166 |
st.write("")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
167 |
st.write("")
|
168 |
st.write("")
|
169 |
-
st.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
import streamlit as st # type: ignore
|
2 |
import os
|
3 |
from datetime import datetime
|
4 |
+
from extra_streamlit_components import tab_bar, TabBarItemData
|
5 |
+
import io
|
6 |
+
import base64
|
7 |
+
from gtts import gTTS
|
8 |
+
import soundfile as sf
|
9 |
+
import sounddevice as sd
|
10 |
+
import numpy as np
|
11 |
+
import scipy.io.wavfile as wav
|
12 |
+
import speech_recognition as sr
|
13 |
+
import time
|
14 |
from sentence_transformers import SentenceTransformer
|
15 |
from translate_app import tr
|
16 |
import getpass
|
|
|
22 |
from langchain_core.messages import BaseMessage, SystemMessage, HumanMessage, AIMessage, trim_messages
|
23 |
from langgraph.graph.message import add_messages
|
24 |
from typing_extensions import Annotated, TypedDict
|
25 |
+
from dotenv import load_dotenv
|
26 |
|
27 |
import warnings
|
28 |
warnings.filterwarnings('ignore')
|
|
|
35 |
os.environ["LANGCHAIN_ENDPOINT"]="https://api.smith.langchain.com"
|
36 |
os.environ["LANGCHAIN_HUB_API_URL"]="https://api.smith.langchain.com"
|
37 |
os.environ["LANGCHAIN_PROJECT"] = "Sales Coaching Chatbot"
|
38 |
+
if st.session_state.Cloud != 0:
|
39 |
+
load_dotenv()
|
40 |
os.getenv("LANGCHAIN_API_KEY")
|
41 |
os.getenv("MISTRAL_API_KEY")
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
|
46 |
model = ChatMistralAI(model="mistral-large-latest")
|
|
|
|
|
|
|
47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
+
language = "French"
|
50 |
prompt = ChatPromptTemplate.from_messages(
|
51 |
[
|
52 |
(
|
53 |
"system",
|
54 |
+
"Répond à toutes les questions du mieux possible en {language}.",
|
55 |
),
|
56 |
MessagesPlaceholder(variable_name="messages"),
|
57 |
]
|
|
|
63 |
|
64 |
def call_model(state: State):
|
65 |
chain = prompt | model
|
66 |
+
response = chain.invoke(state)
|
|
|
|
|
|
|
67 |
return {"messages": [response]}
|
68 |
|
69 |
# Define a new graph
|
|
|
78 |
memory = MemorySaver()
|
79 |
app = workflow.compile(checkpointer=memory)
|
80 |
|
81 |
+
# @st.cache_data
|
82 |
def init():
|
83 |
+
global config,thread_id, context,human_message1,ai_message1,language, app
|
84 |
|
85 |
+
thread_id = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
86 |
config = {"configurable": {"thread_id": thread_id}}
|
87 |
|
88 |
+
context = """Tu es un Directeur Commercial, mal organisé, d'une entreprise qui commercialise une solution technologique B2B. """
|
89 |
+
human_message1 = """Je souhaites que nous ayons une conversation verbale entre un commercial de mon entreprise, Marc (moi), et toi que je prospecte.
|
90 |
Mon entreprise propose une solution logicielle pour gérer la proposition de valeur d’entreprises B2B qui commercialises des solutions technologiques.
|
91 |
|
92 |
Les problématiques adressées par ma solution sont:
|
|
|
119 |
|
120 |
Attention: Ce n'est pas toi qui m'aide, c'est moi qui t'aide avec ma solution.
|
121 |
"""
|
122 |
+
ai_message1 = "J'ai bien compris, je suis un Directeur Commercial prospecté et je réponds seulement à mes questions"
|
123 |
|
124 |
+
context = st.text_area(label=tr("Contexte:"), value=context)
|
125 |
+
human_message1 = st.text_area(label=tr("Consigne"), value=human_message1,height=300)
|
126 |
messages = [
|
127 |
SystemMessage(content=context),
|
128 |
HumanMessage(content=human_message1),
|
129 |
AIMessage(content=ai_message1),
|
130 |
+
HumanMessage(content="")
|
131 |
]
|
132 |
|
133 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
|
135 |
+
app.invoke(
|
136 |
+
{"messages": messages, "language": language},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
137 |
config,
|
138 |
)
|
|
|
|
|
|
|
139 |
'''
|
140 |
+
st.write("**Contexte:** "+context)
|
141 |
+
st.write("")
|
142 |
+
st.write("**Human Message:** "+human_message1)
|
143 |
+
st.write("")
|
144 |
+
st.write("**AI Message:** "+ai_message1)
|
|
|
|
|
|
|
|
|
|
|
|
|
145 |
'''
|
146 |
st.write("")
|
147 |
+
return config, thread_id
|
148 |
+
|
149 |
+
# Fonction pour générer et jouer le texte en speech
|
150 |
+
def play_audio(custom_sentence, Lang_target, speed=1.0):
|
151 |
+
# Générer le speech avec gTTS
|
152 |
+
audio_stream_bytesio_src = io.BytesIO()
|
153 |
+
tts = gTTS(custom_sentence, lang=Lang_target)
|
154 |
+
|
155 |
+
# Revenir au début du flux audio
|
156 |
+
audio_stream_bytesio_src.seek(0)
|
157 |
+
audio_stream_bytesio_src.truncate(0)
|
158 |
+
|
159 |
+
tts.write_to_fp(audio_stream_bytesio_src)
|
160 |
+
|
161 |
+
audio_stream_bytesio_src.seek(0)
|
162 |
+
|
163 |
+
# Charger l'audio dans un tableau numpy
|
164 |
+
data, samplerate = sf.read(audio_stream_bytesio_src)
|
165 |
+
|
166 |
+
# Modifier la vitesse de lecture en ajustant le taux d'échantillonnage
|
167 |
+
new_samplerate = int(samplerate * speed)
|
168 |
+
new_audio_stream_bytesio = io.BytesIO()
|
169 |
+
|
170 |
+
# Enregistrer l'audio avec la nouvelle fréquence d'échantillonnage
|
171 |
+
sf.write(new_audio_stream_bytesio, data, new_samplerate, format='wav')
|
172 |
+
new_audio_stream_bytesio.seek(0)
|
173 |
+
|
174 |
+
# Lire l'audio dans Streamlit
|
175 |
+
st.audio(new_audio_stream_bytesio, autoplay=True)
|
176 |
+
|
177 |
+
def is_silent(data, threshold=0.01):
|
178 |
+
"""Vérifie si le niveau audio est inférieur à un certain seuil (silence)"""
|
179 |
+
return np.abs(data).mean() < threshold
|
180 |
+
|
181 |
+
def record_audio_until_silence(fs=44100, silence_duration=2):
|
182 |
+
# st.write("Enregistrement en cours... Parlez maintenant.")
|
183 |
+
audio_data = []
|
184 |
+
silence_start = None
|
185 |
+
|
186 |
+
while True:
|
187 |
+
# Enregistre un petit bout de son
|
188 |
+
data = sd.rec(int(fs * 2), samplerate=fs, channels=1, dtype='float32')
|
189 |
+
sd.wait()
|
190 |
+
|
191 |
+
# Ajoute le morceau au tableau d'audio
|
192 |
+
audio_data.append(data)
|
193 |
+
|
194 |
+
# Vérifie si le morceau est en silence
|
195 |
+
if is_silent(data):
|
196 |
+
if silence_start is None:
|
197 |
+
silence_start = time.time() # Démarre le chronomètre du silence
|
198 |
+
elif time.time() - silence_start > silence_duration:
|
199 |
+
print("Silence détecté. Fin de l'enregistrement.")
|
200 |
+
break # Arrête l'enregistrement si le silence dure suffisamment longtemps
|
201 |
+
else:
|
202 |
+
silence_start = None # Réinitialise le chronomètre si le son est détecté
|
203 |
+
|
204 |
+
# Convertit la liste de tableaux en un seul tableau NumPy
|
205 |
+
audio_data = np.concatenate(audio_data)
|
206 |
+
audio_data = np.int16(audio_data * 32767)
|
207 |
+
|
208 |
+
# Sauvegarde le fichier audio en format WAV
|
209 |
+
wav.write("enregistrement.wav", fs, audio_data)
|
210 |
+
st.write("Enregistrement sauvegardé")
|
211 |
+
|
212 |
+
def convert_audio_to_text(filename):
|
213 |
+
recognizer = sr.Recognizer()
|
214 |
+
with sr.AudioFile(filename) as source:
|
215 |
+
audio = recognizer.record(source) # Lit le fichier audio
|
216 |
+
|
217 |
+
try:
|
218 |
+
# Utilise l'API Google pour la reconnaissance vocale
|
219 |
+
text = recognizer.recognize_google(audio, language='fr-FR')
|
220 |
+
return text
|
221 |
+
except sr.UnknownValueError:
|
222 |
+
st.write("Google Speech Recognition n'a pas pu comprendre l'audio.")
|
223 |
+
return ""
|
224 |
+
except sr.RequestError as e:
|
225 |
+
st.write(f"Erreur avec le service Google Speech Recognition; {e}")
|
226 |
+
return ""
|
227 |
+
|
228 |
+
|
229 |
+
def run():
|
230 |
+
global thread_id, config
|
231 |
+
|
232 |
st.write("")
|
233 |
st.write("")
|
234 |
+
st.title(tr(title))
|
235 |
+
|
236 |
+
chosen_id = tab_bar(data=[
|
237 |
+
TabBarItemData(id="tab1", title=tr("Initialisation"), description=tr("d'une nouvelle conversation")),
|
238 |
+
TabBarItemData(id="tab2", title=tr("Conversation"), description=tr("avec le prospect"))],
|
239 |
+
default="tab1")
|
240 |
+
|
241 |
+
|
242 |
+
if (chosen_id == "tab1"):
|
243 |
+
config,thread_id = init()
|
244 |
+
query = ""
|
245 |
+
st.button(label=tr("Validez"), type="primary")
|
246 |
+
else:
|
247 |
+
try:
|
248 |
+
config
|
249 |
+
# On ne fait rien
|
250 |
+
except NameError:
|
251 |
+
config,thread_id = init()
|
252 |
+
|
253 |
+
st.write("**thread_id:** "+thread_id)
|
254 |
+
# query = st.text_area(label=tr("Vendeur:"), value="")
|
255 |
+
query = ""
|
256 |
+
if st.button(label=tr("Cliquer pour enregistrer"), type="primary"):
|
257 |
+
record_audio_until_silence() # Enregistre jusqu'à ce qu'il y ait 2 secondes de silence
|
258 |
+
query = convert_audio_to_text("enregistrement.wav") # Convertit l'audio en texte
|
259 |
+
st.write("**Vendeur :** "+query)
|
260 |
+
# st.button(label=tr("Validez"), type="primary")
|
261 |
+
input_messages = [HumanMessage(query)]
|
262 |
+
|
263 |
+
if query != "":
|
264 |
+
output = app.invoke(
|
265 |
+
{"messages": input_messages, "language": language},
|
266 |
+
config,
|
267 |
+
)
|
268 |
+
st.write("**Prospect :** "+output["messages"][-1].content)
|
269 |
+
# Fonction pour générer et jouer le texte en speech
|
270 |
+
|
271 |
+
|
272 |
+
# Prononciation de la réponse
|
273 |
+
custom_sentence = output["messages"][-1].content
|
274 |
+
Lang_target = "fr" # Exemple de langue détectée
|
275 |
+
# Joue l'audio
|
276 |
+
play_audio(custom_sentence, Lang_target, 1)
|
277 |
+
|
278 |
+
|
279 |
+
'''
|
280 |
+
# Créer un espace réservé pour afficher les tokens
|
281 |
+
placeholder = st.empty()
|
282 |
+
|
283 |
+
for chunk, metadata in app.stream(
|
284 |
+
{"messages": input_messages, "language": language},
|
285 |
+
config,
|
286 |
+
stream_mode="messages",
|
287 |
+
):
|
288 |
+
if isinstance(chunk, AIMessage): # Filter to just model responses
|
289 |
+
# st.markdown("<span style='white-space: nowrap;'>"+"/"+chunk.content+"/"+"</span>", unsafe_allow_html=True)
|
290 |
+
placeholder.markdown(f"<p style='display: inline;'>{chunk.content}</p>", unsafe_allow_html=True)
|
291 |
+
'''
|
292 |
+
st.write("")
|
293 |
+
st.write("")
|
294 |
+
st.write("")
|
295 |
+
st.write("")
|
tabs/intro.py
CHANGED
@@ -7,6 +7,7 @@ sidebar_name = "Introduction"
|
|
7 |
|
8 |
def run():
|
9 |
|
|
|
10 |
st.write("")
|
11 |
# TODO: choose between one of these GIFs
|
12 |
# st.image("https://dst-studio-template.s3.eu-west-3.amazonaws.com/1.gif")
|
|
|
7 |
|
8 |
def run():
|
9 |
|
10 |
+
st.write("")
|
11 |
st.write("")
|
12 |
# TODO: choose between one of these GIFs
|
13 |
# st.image("https://dst-studio-template.s3.eu-west-3.amazonaws.com/1.gif")
|
tabs/sentence_similarity_tab.py
CHANGED
@@ -6,7 +6,6 @@ import contextlib
|
|
6 |
import numpy as np
|
7 |
import pandas as pd
|
8 |
import matplotlib.pyplot as plt
|
9 |
-
from nltk.corpus import stopwords
|
10 |
from sklearn.manifold import TSNE
|
11 |
from sentence_transformers import SentenceTransformer
|
12 |
from sklearn.metrics.pairwise import cosine_similarity
|
@@ -18,6 +17,7 @@ dataPath = st.session_state.DataPath
|
|
18 |
|
19 |
|
20 |
def run():
|
|
|
21 |
st.write("")
|
22 |
st.title(tr(title))
|
23 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
|
|
6 |
import numpy as np
|
7 |
import pandas as pd
|
8 |
import matplotlib.pyplot as plt
|
|
|
9 |
from sklearn.manifold import TSNE
|
10 |
from sentence_transformers import SentenceTransformer
|
11 |
from sklearn.metrics.pairwise import cosine_similarity
|
|
|
17 |
|
18 |
|
19 |
def run():
|
20 |
+
st.write("")
|
21 |
st.write("")
|
22 |
st.title(tr(title))
|
23 |
sentences = ["This is an example sentence", "Each sentence is converted"]
|
tabs/speech2text_tab.py
CHANGED
@@ -2,15 +2,10 @@ import streamlit as st # type: ignore
|
|
2 |
import os
|
3 |
import pandas as pd
|
4 |
import collections
|
5 |
-
from nltk.tokenize import word_tokenize
|
6 |
-
from nltk import download
|
7 |
from ast import literal_eval
|
8 |
from translate_app import tr
|
9 |
if st.session_state.Cloud == 0:
|
10 |
-
# import nltk
|
11 |
import contextlib
|
12 |
-
import re
|
13 |
-
from nltk.corpus import stopwords
|
14 |
import warnings
|
15 |
warnings.filterwarnings('ignore')
|
16 |
# from PIL import Image
|
@@ -20,308 +15,7 @@ if st.session_state.Cloud == 0:
|
|
20 |
title = "Speech 2 Text"
|
21 |
sidebar_name = "Speech 2 Text"
|
22 |
dataPath = st.session_state.DataPath
|
23 |
-
'''
|
24 |
-
# Indiquer si l'on veut enlever les stop words. C'est un processus long
|
25 |
-
stopwords_to_do = True
|
26 |
-
# Indiquer si l'on veut lemmatiser les phrases, un fois les stop words enlevés. C'est un processus long (approximativement 8 minutes)
|
27 |
-
lemmatize_to_do = True
|
28 |
-
# Indiquer si l'on veut calculer le score Bleu pour tout le corpus. C'est un processus très long long (approximativement 10 minutes pour les 10 dictionnaires)
|
29 |
-
bleu_score_to_do = True
|
30 |
-
# Première ligne à charger
|
31 |
-
first_line = 0
|
32 |
-
# Nombre maximum de lignes à charger
|
33 |
-
max_lines = 140000
|
34 |
-
if ((first_line+max_lines)>137860):
|
35 |
-
max_lines = max(137860-first_line ,0)
|
36 |
-
# Nombre maximum de ligne à afficher pour les DataFrame
|
37 |
-
max_lines_to_display = 50
|
38 |
|
39 |
-
download('punkt')
|
40 |
-
|
41 |
-
if st.session_state.Cloud == 0:
|
42 |
-
download('averaged_perceptron_tagger')
|
43 |
-
with contextlib.redirect_stdout(open(os.devnull, "w")):
|
44 |
-
download('stopwords')
|
45 |
-
|
46 |
-
@st.cache_data
|
47 |
-
def load_data(path):
|
48 |
-
|
49 |
-
input_file = os.path.join(path)
|
50 |
-
with open(input_file, "r", encoding="utf-8") as f:
|
51 |
-
data = f.read()
|
52 |
-
|
53 |
-
# On convertit les majuscules en minulcule
|
54 |
-
data = data.lower()
|
55 |
-
data = data.split('\n')
|
56 |
-
return data[first_line:min(len(data),first_line+max_lines)]
|
57 |
-
|
58 |
-
@st.cache_data
|
59 |
-
def load_preprocessed_data(path,data_type):
|
60 |
-
|
61 |
-
input_file = os.path.join(path)
|
62 |
-
if data_type == 1:
|
63 |
-
return pd.read_csv(input_file, encoding="utf-8", index_col=0)
|
64 |
-
else:
|
65 |
-
with open(input_file, "r", encoding="utf-8") as f:
|
66 |
-
data = f.read()
|
67 |
-
data = data.split('\n')
|
68 |
-
if data_type==0:
|
69 |
-
data=data[:-1]
|
70 |
-
elif data_type == 2:
|
71 |
-
data=[eval(i) for i in data[:-1]]
|
72 |
-
elif data_type ==3:
|
73 |
-
data2 = []
|
74 |
-
for d in data[:-1]:
|
75 |
-
data2.append(literal_eval(d))
|
76 |
-
data=data2
|
77 |
-
return data
|
78 |
-
|
79 |
-
@st.cache_data
|
80 |
-
def load_all_preprocessed_data(lang):
|
81 |
-
txt =load_preprocessed_data(dataPath+'/preprocess_txt_'+lang,0)
|
82 |
-
txt_split = load_preprocessed_data(dataPath+'/preprocess_txt_split_'+lang,3)
|
83 |
-
txt_lem = load_preprocessed_data(dataPath+'/preprocess_txt_lem_'+lang,0)
|
84 |
-
txt_wo_stopword = load_preprocessed_data(dataPath+'/preprocess_txt_wo_stopword_'+lang,0)
|
85 |
-
df_count_word = pd.concat([load_preprocessed_data(dataPath+'/preprocess_df_count_word1_'+lang,1), load_preprocessed_data(dataPath+'/preprocess_df_count_word2_'+lang,1)])
|
86 |
-
return txt, txt_split, txt_lem, txt_wo_stopword, df_count_word
|
87 |
-
|
88 |
-
#Chargement des textes complet dans les 2 langues
|
89 |
-
full_txt_en = load_data(dataPath+'/small_vocab_en')
|
90 |
-
full_txt_fr = load_data(dataPath+'/small_vocab_fr')
|
91 |
-
|
92 |
-
# Chargement du résultat du préprocessing, si st.session_state.reCalcule == False
|
93 |
-
if not st.session_state.reCalcule:
|
94 |
-
full_txt_en, full_txt_split_en, full_txt_lem_en, full_txt_wo_stopword_en, full_df_count_word_en = load_all_preprocessed_data('en')
|
95 |
-
full_txt_fr, full_txt_split_fr, full_txt_lem_fr, full_txt_wo_stopword_fr, full_df_count_word_fr = load_all_preprocessed_data('fr')
|
96 |
-
else:
|
97 |
-
|
98 |
-
def remove_stopwords(text, lang):
|
99 |
-
stop_words = set(stopwords.words(lang))
|
100 |
-
# stop_words will contain set all english stopwords
|
101 |
-
filtered_sentence = []
|
102 |
-
for word in text.split():
|
103 |
-
if word not in stop_words:
|
104 |
-
filtered_sentence.append(word)
|
105 |
-
return " ".join(filtered_sentence)
|
106 |
-
|
107 |
-
def clean_undesirable_from_text(sentence, lang):
|
108 |
-
|
109 |
-
# Removing URLs
|
110 |
-
sentence = re.sub(r"https?://\S+|www\.\S+", "", sentence )
|
111 |
-
|
112 |
-
# Removing Punctuations (we keep the . character)
|
113 |
-
REPLACEMENTS = [("..", "."),
|
114 |
-
(",", ""),
|
115 |
-
(";", ""),
|
116 |
-
(":", ""),
|
117 |
-
("?", ""),
|
118 |
-
('"', ""),
|
119 |
-
("-", " "),
|
120 |
-
("it's", "it is"),
|
121 |
-
("isn't","is not"),
|
122 |
-
("'", " ")
|
123 |
-
]
|
124 |
-
for old, new in REPLACEMENTS:
|
125 |
-
sentence = sentence.replace(old, new)
|
126 |
-
|
127 |
-
# Removing Digits
|
128 |
-
sentence= re.sub(r'[0-9]','',sentence)
|
129 |
-
|
130 |
-
# Removing Additional Spaces
|
131 |
-
sentence = re.sub(' +', ' ', sentence)
|
132 |
-
|
133 |
-
return sentence
|
134 |
-
|
135 |
-
def clean_untranslated_sentence(data1, data2):
|
136 |
-
i=0
|
137 |
-
while i<len(data1):
|
138 |
-
if data1[i]==data2[i]:
|
139 |
-
data1.pop(i)
|
140 |
-
data2.pop(i)
|
141 |
-
else: i+=1
|
142 |
-
return data1,data2
|
143 |
-
|
144 |
-
import spacy
|
145 |
-
|
146 |
-
nlp_en = spacy.load('en_core_web_sm')
|
147 |
-
nlp_fr = spacy.load('fr_core_news_sm')
|
148 |
-
|
149 |
-
|
150 |
-
def lemmatize(sentence,lang):
|
151 |
-
# Create a Doc object
|
152 |
-
if lang=='en':
|
153 |
-
nlp=nlp_en
|
154 |
-
elif lang=='fr':
|
155 |
-
nlp=nlp_fr
|
156 |
-
else: return
|
157 |
-
doc = nlp(sentence)
|
158 |
-
|
159 |
-
# Create list of tokens from given string
|
160 |
-
tokens = []
|
161 |
-
for token in doc:
|
162 |
-
tokens.append(token)
|
163 |
-
|
164 |
-
lemmatized_sentence = " ".join([token.lemma_ for token in doc])
|
165 |
-
|
166 |
-
return lemmatized_sentence
|
167 |
-
|
168 |
-
|
169 |
-
def preprocess_txt (data, lang):
|
170 |
-
|
171 |
-
word_count = collections.Counter()
|
172 |
-
word_lem_count = collections.Counter()
|
173 |
-
word_wosw_count = collections.Counter()
|
174 |
-
corpus = []
|
175 |
-
data_split = []
|
176 |
-
sentence_length = []
|
177 |
-
data_split_wo_stopwords = []
|
178 |
-
data_length_wo_stopwords = []
|
179 |
-
data_lem = []
|
180 |
-
data_lem_length = []
|
181 |
-
|
182 |
-
txt_en_one_string= ". ".join([s for s in data])
|
183 |
-
txt_en_one_string = txt_en_one_string.replace('..', '.')
|
184 |
-
txt_en_one_string = " "+clean_undesirable_from_text(txt_en_one_string, 'lang')
|
185 |
-
data = txt_en_one_string.split('.')
|
186 |
-
if data[-1]=="":
|
187 |
-
data.pop(-1)
|
188 |
-
for i in range(len(data)): # On enleve les ' ' qui commencent et finissent les phrases
|
189 |
-
if data[i][0] == ' ':
|
190 |
-
data[i]=data[i][1:]
|
191 |
-
if data[i][-1] == ' ':
|
192 |
-
data[i]=data[i][:-1]
|
193 |
-
nb_phrases = len(data)
|
194 |
-
|
195 |
-
# Création d'un tableau de mots (sentence_split)
|
196 |
-
for i,sentence in enumerate(data):
|
197 |
-
sentence_split = word_tokenize(sentence)
|
198 |
-
word_count.update(sentence_split)
|
199 |
-
data_split.append(sentence_split)
|
200 |
-
sentence_length.append(len(sentence_split))
|
201 |
-
|
202 |
-
# La lemmatisation et le nettoyage des stopword va se faire en batch pour des raisons de vitesse
|
203 |
-
# (au lieu de le faire phrase par phrase)
|
204 |
-
# Ces 2 processus nécéssitent de connaitre la langue du corpus
|
205 |
-
if lang == 'en': l='english'
|
206 |
-
elif lang=='fr': l='french'
|
207 |
-
else: l="unknown"
|
208 |
-
|
209 |
-
if l!="unknown":
|
210 |
-
# Lemmatisation en 12 lots (On ne peut lemmatiser + de 1 M de caractères à la fois)
|
211 |
-
data_lemmatized=""
|
212 |
-
if lemmatize_to_do:
|
213 |
-
n_batch = 12
|
214 |
-
batch_size = round((nb_phrases/ n_batch)+0.5)
|
215 |
-
for i in range(n_batch):
|
216 |
-
to_lem = ".".join([s for s in data[i*batch_size:(i+1)*batch_size]])
|
217 |
-
data_lemmatized = data_lemmatized+"."+lemmatize(to_lem,lang).lower()
|
218 |
-
|
219 |
-
data_lem_for_sw = data_lemmatized[1:]
|
220 |
-
data_lemmatized = data_lem_for_sw.split('.')
|
221 |
-
for i in range(nb_phrases):
|
222 |
-
data_lem.append(data_lemmatized[i].split())
|
223 |
-
data_lem_length.append(len(data_lemmatized[i].split()))
|
224 |
-
word_lem_count.update(data_lem[-1])
|
225 |
-
|
226 |
-
# Elimination des StopWords en un lot
|
227 |
-
# On élimine les Stopwords des phrases lémmatisés, si cette phase a eu lieu
|
228 |
-
# (wosw signifie "WithOut Stop Words")
|
229 |
-
if stopwords_to_do:
|
230 |
-
if lemmatize_to_do:
|
231 |
-
data_wosw = remove_stopwords(data_lem_for_sw,l)
|
232 |
-
else:
|
233 |
-
data_wosw = remove_stopwords(txt_en_one_string,l)
|
234 |
-
|
235 |
-
data_wosw = data_wosw.split('.')
|
236 |
-
for i in range(nb_phrases):
|
237 |
-
data_split_wo_stopwords.append(data_wosw[i].split())
|
238 |
-
data_length_wo_stopwords.append(len(data_wosw[i].split()))
|
239 |
-
word_wosw_count.update(data_split_wo_stopwords[-1])
|
240 |
-
|
241 |
-
corpus = list(word_count.keys())
|
242 |
-
|
243 |
-
# Création d'un DataFrame txt_n_unique_val :
|
244 |
-
# colonnes = mots
|
245 |
-
# lignes = phases
|
246 |
-
# valeur de la cellule = nombre d'occurence du mot dans la phrase
|
247 |
-
|
248 |
-
## BOW
|
249 |
-
from sklearn.feature_extraction.text import CountVectorizer
|
250 |
-
count_vectorizer = CountVectorizer(analyzer="word", ngram_range=(1, 1), token_pattern=r"[^' ']+" )
|
251 |
-
|
252 |
-
# Calcul du nombre d'apparition de chaque mot dans la phrases
|
253 |
-
countvectors = count_vectorizer.fit_transform(data)
|
254 |
-
corpus = count_vectorizer.get_feature_names_out()
|
255 |
-
|
256 |
-
txt_n_unique_val= pd.DataFrame(columns=corpus,index=range(nb_phrases), data=countvectors.todense()).astype(float)
|
257 |
-
|
258 |
-
return data, corpus, data_split, data_lemmatized, data_wosw, txt_n_unique_val, sentence_length, data_length_wo_stopwords, data_lem_length
|
259 |
-
|
260 |
-
|
261 |
-
def count_world(data):
|
262 |
-
word_count = collections.Counter()
|
263 |
-
for sentence in data:
|
264 |
-
word_count.update(word_tokenize(sentence))
|
265 |
-
corpus = list(word_count.keys())
|
266 |
-
nb_mots = sum(word_count.values())
|
267 |
-
nb_mots_uniques = len(corpus)
|
268 |
-
return corpus, nb_mots, nb_mots_uniques
|
269 |
-
|
270 |
-
def display_preprocess_results(lang, data, data_split, data_lem, data_wosw, txt_n_unique_val):
|
271 |
-
|
272 |
-
global max_lines, first_line, last_line, lemmatize_to_do, stopwords_to_do
|
273 |
-
corpus = []
|
274 |
-
nb_phrases = len(data)
|
275 |
-
corpus, nb_mots, nb_mots_uniques = count_world(data)
|
276 |
-
mots_lem, _ , nb_mots_lem = count_world(data_lem)
|
277 |
-
mots_wo_sw, _ , nb_mots_wo_stopword = count_world(data_wosw)
|
278 |
-
# Identifiez les colonnes contenant uniquement des zéros et les supprimer
|
279 |
-
columns_with_only_zeros = txt_n_unique_val.columns[txt_n_unique_val.eq(0).all()]
|
280 |
-
txt_n_unique_val = txt_n_unique_val.drop(columns=columns_with_only_zeros)
|
281 |
-
|
282 |
-
# Affichage du nombre de mot en fonction du pré-processing réalisé
|
283 |
-
tab1, tab2, tab3, tab4 = st.tabs([tr("Résumé"), tr("Tokenisation"),tr("Lemmatisation"), tr("Sans Stopword")])
|
284 |
-
with tab1:
|
285 |
-
st.subheader(tr("Résumé du pré-processing"))
|
286 |
-
st.write("**"+tr("Nombre de phrases")+" : "+str(nb_phrases)+"**")
|
287 |
-
st.write("**"+tr("Nombre de mots")+" : "+str(nb_mots)+"**")
|
288 |
-
st.write("**"+tr("Nombre de mots uniques")+" : "+str(nb_mots_uniques)+"**")
|
289 |
-
st.write("")
|
290 |
-
st.write("\n**"+tr("Nombre d'apparitions de chaque mot dans chaque phrase (:red[Bag Of Words]):")+"**")
|
291 |
-
st.dataframe(txt_n_unique_val.head(max_lines_to_display), width=800)
|
292 |
-
with tab2:
|
293 |
-
st.subheader(tr("Tokenisation"))
|
294 |
-
st.write(tr('Texte "splited":'))
|
295 |
-
st.dataframe(pd.DataFrame(data=data_split, index=range(first_line,last_line)).head(max_lines_to_display).fillna(''), width=800)
|
296 |
-
st.write("**"+tr("Nombre de mots uniques")+" : "+str(nb_mots_uniques)+"**")
|
297 |
-
st.write("")
|
298 |
-
st.write("\n**"+tr("Mots uniques")+":**")
|
299 |
-
st.markdown(corpus[:500])
|
300 |
-
st.write("\n**"+tr("Nombre d'apparitions de chaque mot dans chaque phrase (:red[Bag Of Words]):")+"**")
|
301 |
-
st.dataframe(txt_n_unique_val.head(max_lines_to_display), width=800)
|
302 |
-
with tab3:
|
303 |
-
st.subheader(tr("Lemmatisation"))
|
304 |
-
if lemmatize_to_do:
|
305 |
-
st.dataframe(pd.DataFrame(data=data_lem,columns=[tr('Texte lemmatisé')],index=range(first_line,last_line)).head(max_lines_to_display), width=800)
|
306 |
-
# Si langue anglaise, affichage du taggage des mots
|
307 |
-
# if lang == 'en':
|
308 |
-
# for i in range(min(5,len(data))):
|
309 |
-
# s = str(nltk.pos_tag(data_split[i]))
|
310 |
-
# st.markdown("**Texte avec Tags "+str(i)+"** : "+s)
|
311 |
-
st.write("**"+tr("Nombre de mots uniques lemmatisés")+" : "+str(nb_mots_lem)+"**")
|
312 |
-
st.write("")
|
313 |
-
st.write("\n**"+tr("Mots uniques lemmatisés:")+"**")
|
314 |
-
st.markdown(mots_lem[:500])
|
315 |
-
with tab4:
|
316 |
-
st.subheader(tr("Sans Stopword"))
|
317 |
-
if stopwords_to_do:
|
318 |
-
st.dataframe(pd.DataFrame(data=data_wosw,columns=['Texte sans stopwords'],index=range(first_line,last_line)).head(max_lines_to_display), width=800)
|
319 |
-
st.write("**"+tr("Nombre de mots uniques sans stop words")+": "+str(nb_mots_wo_stopword)+"**")
|
320 |
-
st.write("")
|
321 |
-
st.write("\n**"+tr("Mots uniques sans stop words")+":**")
|
322 |
-
st.markdown(mots_wo_sw[:500])
|
323 |
-
|
324 |
-
'''
|
325 |
def run():
|
326 |
global max_lines, first_line, last_line, lemmatize_to_do, stopwords_to_do
|
327 |
global full_txt_en, full_txt_split_en, full_txt_lem_en, full_txt_wo_stopword_en, full_df_count_word_en
|
@@ -329,89 +23,6 @@ def run():
|
|
329 |
|
330 |
st.write("")
|
331 |
st.title(tr(title))
|
332 |
-
'''
|
333 |
-
st.write("## **"+tr("Explications")+" :**\n")
|
334 |
-
st.markdown(tr(
|
335 |
-
"""
|
336 |
-
Le traitement du langage naturel permet à l'ordinateur de comprendre et de traiter les langues humaines.
|
337 |
-
Lors de notre projet, nous avons étudié le dataset small_vocab, proposés par Suzan Li, Chief Data Scientist chez Campaign Research à Toronto.
|
338 |
-
Celui-ci représente un corpus de phrases simples en anglais, et sa traduction (approximative) en français.
|
339 |
-
:red[**Small_vocab**] contient 137 860 phrases en anglais et français.
|
340 |
-
""")
|
341 |
-
, unsafe_allow_html=True)
|
342 |
-
st.markdown(tr(
|
343 |
-
"""
|
344 |
-
Afin de découvrir ce corpus et de préparer la traduction, nous allons effectuer un certain nombre de tâches de pré-traitement (preprocessing).
|
345 |
-
Ces taches sont, par exemple:
|
346 |
-
""")
|
347 |
-
, unsafe_allow_html=True)
|
348 |
-
st.markdown(
|
349 |
-
"* "+tr("le :red[**nettoyage**] du texte (enlever les majuscules et la ponctuation)")+"\n"+ \
|
350 |
-
"* "+tr("la :red[**tokenisation**] (découpage du texte en mots)")+"\n"+ \
|
351 |
-
"* "+tr("la :red[**lemmatisation**] (traitement lexical qui permet de donner une forme unique à toutes les \"variations\" d'un même mot)")+"\n"+ \
|
352 |
-
"* "+tr("l'élimination des :red[**mots \"transparents\"**] (sans utilité pour la compréhension, tels que les articles).")+" \n"+ \
|
353 |
-
tr("Ce prétraintement se conclut avec la contruction d'un :red[**Bag Of Worlds**], c'est à dire une matrice qui compte le nombre d'apparition de chaque mots (colonne) dans chaque phrase (ligne)")
|
354 |
-
, unsafe_allow_html=True)
|
355 |
-
#
|
356 |
-
st.write("## **"+tr("Paramètres")+" :**\n")
|
357 |
-
Langue = st.radio(tr('Langue:'),('Anglais','Français'), horizontal=True)
|
358 |
-
first_line = st.slider(tr('No de la premiere ligne à analyser:'),0,137859)
|
359 |
-
max_lines = st.select_slider(tr('Nombre de lignes à analyser:'),
|
360 |
-
options=[1,5,10,15,100, 500, 1000,'Max'])
|
361 |
-
if max_lines=='Max':
|
362 |
-
max_lines=137860
|
363 |
-
if ((first_line+max_lines)>137860):
|
364 |
-
max_lines = max(137860-first_line,0)
|
365 |
-
|
366 |
-
last_line = first_line+max_lines
|
367 |
-
if (Langue=='Anglais'):
|
368 |
-
st.dataframe(pd.DataFrame(data=full_txt_en,columns=['Texte']).loc[first_line:last_line-1].head(max_lines_to_display), width=800)
|
369 |
-
else:
|
370 |
-
st.dataframe(pd.DataFrame(data=full_txt_fr,columns=['Texte']).loc[first_line:last_line-1].head(max_lines_to_display), width=800)
|
371 |
-
st.write("")
|
372 |
-
|
373 |
-
# Chargement des textes sélectionnés dans les 2 langues (max lignes = max_lines)
|
374 |
-
txt_en = full_txt_en[first_line:last_line]
|
375 |
-
txt_fr = full_txt_fr[first_line:last_line]
|
376 |
-
|
377 |
-
# Elimination des phrases non traduites
|
378 |
-
# txt_en, txt_fr = clean_untranslated_sentence(txt_en, txt_fr)
|
379 |
-
|
380 |
-
if not st.session_state.reCalcule:
|
381 |
-
txt_split_en = full_txt_split_en[first_line:last_line]
|
382 |
-
txt_lem_en = full_txt_lem_en[first_line:last_line]
|
383 |
-
txt_wo_stopword_en = full_txt_wo_stopword_en[first_line:last_line]
|
384 |
-
df_count_word_en = full_df_count_word_en.loc[first_line:last_line-1]
|
385 |
-
txt_split_fr = full_txt_split_fr[first_line:last_line]
|
386 |
-
txt_lem_fr = full_txt_lem_fr[first_line:last_line]
|
387 |
-
txt_wo_stopword_fr = full_txt_wo_stopword_fr[first_line:last_line]
|
388 |
-
df_count_word_fr = full_df_count_word_fr.loc[first_line:last_line-1]
|
389 |
-
|
390 |
-
# Lancement du préprocessing du texte qui va spliter nettoyer les phrases et les spliter en mots
|
391 |
-
# et calculer nombre d'occurences des mots dans chaque phrase
|
392 |
-
if (Langue == 'Anglais'):
|
393 |
-
st.write("## **"+tr("Préprocessing de small_vocab_en")+" :**\n")
|
394 |
-
if max_lines>10000:
|
395 |
-
with st.status(":sunglasses:", expanded=True):
|
396 |
-
if st.session_state.reCalcule:
|
397 |
-
txt_en, corpus_en, txt_split_en, txt_lem_en, txt_wo_stopword_en, df_count_word_en,sent_len_en, sent_wo_sw_len_en, sent_lem_len_en = preprocess_txt (txt_en,'en')
|
398 |
-
display_preprocess_results('en',txt_en, txt_split_en, txt_lem_en, txt_wo_stopword_en, df_count_word_en)
|
399 |
-
else:
|
400 |
-
if st.session_state.reCalcule:
|
401 |
-
txt_en, corpus_en, txt_split_en, txt_lem_en, txt_wo_stopword_en, df_count_word_en,sent_len_en, sent_wo_sw_len_en, sent_lem_len_en = preprocess_txt (txt_en,'en')
|
402 |
-
display_preprocess_results('en',txt_en, txt_split_en, txt_lem_en, txt_wo_stopword_en, df_count_word_en)
|
403 |
-
else:
|
404 |
-
st.write("## **"+tr("Préprocessing de small_vocab_fr")+" :**\n")
|
405 |
-
if max_lines>10000:
|
406 |
-
with st.status(":sunglasses:", expanded=True):
|
407 |
-
if st.session_state.reCalcule:
|
408 |
-
txt_fr, corpus_fr, txt_split_fr, txt_lem_fr, txt_wo_stopword_fr, df_count_word_fr,sent_len_fr, sent_wo_sw_len_fr, sent_lem_len_fr = preprocess_txt (txt_fr,'fr')
|
409 |
-
display_preprocess_results('fr', txt_fr, txt_split_fr, txt_lem_fr, txt_wo_stopword_fr, df_count_word_fr)
|
410 |
-
else:
|
411 |
-
if st.session_state.reCalcule:
|
412 |
-
txt_fr, corpus_fr, txt_split_fr, txt_lem_fr, txt_wo_stopword_fr, df_count_word_fr,sent_len_fr, sent_wo_sw_len_fr, sent_lem_len_fr = preprocess_txt (txt_fr,'fr')
|
413 |
-
display_preprocess_results('fr', txt_fr, txt_split_fr, txt_lem_fr, txt_wo_stopword_fr, df_count_word_fr)
|
414 |
-
'''
|
415 |
|
416 |
|
417 |
|
|
|
2 |
import os
|
3 |
import pandas as pd
|
4 |
import collections
|
|
|
|
|
5 |
from ast import literal_eval
|
6 |
from translate_app import tr
|
7 |
if st.session_state.Cloud == 0:
|
|
|
8 |
import contextlib
|
|
|
|
|
9 |
import warnings
|
10 |
warnings.filterwarnings('ignore')
|
11 |
# from PIL import Image
|
|
|
15 |
title = "Speech 2 Text"
|
16 |
sidebar_name = "Speech 2 Text"
|
17 |
dataPath = st.session_state.DataPath
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
def run():
|
20 |
global max_lines, first_line, last_line, lemmatize_to_do, stopwords_to_do
|
21 |
global full_txt_en, full_txt_split_en, full_txt_lem_en, full_txt_wo_stopword_en, full_df_count_word_en
|
|
|
23 |
|
24 |
st.write("")
|
25 |
st.title(tr(title))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
|
27 |
|
28 |
|