Spaces:
Build error
Build error
Paulie-Aditya
commited on
Commit
•
10b09df
1
Parent(s):
d1f4023
Upload folder using huggingface_hub
Browse files- .gitignore +5 -0
- requirements.txt +91 -0
- translator.ipynb +452 -0
.gitignore
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
secret.py
|
2 |
+
__pycache__
|
3 |
+
.venv
|
4 |
+
flagged
|
5 |
+
*.github
|
requirements.txt
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
aiofiles==23.2.1
|
2 |
+
altair==5.3.0
|
3 |
+
annotated-types==0.7.0
|
4 |
+
anyio==4.4.0
|
5 |
+
attrs==23.2.0
|
6 |
+
blinker==1.6.3
|
7 |
+
certifi==2023.7.22
|
8 |
+
charset-normalizer==3.3.1
|
9 |
+
click==8.1.7
|
10 |
+
colorama==0.4.6
|
11 |
+
contourpy==1.2.1
|
12 |
+
cycler==0.12.1
|
13 |
+
dnspython==2.6.1
|
14 |
+
email_validator==2.1.1
|
15 |
+
fastapi==0.111.0
|
16 |
+
fastapi-cli==0.0.4
|
17 |
+
ffmpy==0.3.2
|
18 |
+
filelock==3.13.0
|
19 |
+
Flask==3.0.0
|
20 |
+
fonttools==4.52.4
|
21 |
+
fsspec==2023.10.0
|
22 |
+
gradio==4.32.0
|
23 |
+
gradio_client==0.17.0
|
24 |
+
h11==0.14.0
|
25 |
+
httpcore==1.0.5
|
26 |
+
httptools==0.6.1
|
27 |
+
httpx==0.27.0
|
28 |
+
huggingface-hub==0.17.3
|
29 |
+
idna==3.4
|
30 |
+
importlib_resources==6.4.0
|
31 |
+
intel-openmp==2021.4.0
|
32 |
+
itsdangerous==2.1.2
|
33 |
+
Jinja2==3.1.2
|
34 |
+
joblib==1.3.2
|
35 |
+
jsonschema==4.22.0
|
36 |
+
jsonschema-specifications==2023.12.1
|
37 |
+
kiwisolver==1.4.5
|
38 |
+
markdown-it-py==3.0.0
|
39 |
+
MarkupSafe==2.1.3
|
40 |
+
matplotlib==3.9.0
|
41 |
+
mdurl==0.1.2
|
42 |
+
mkl==2021.4.0
|
43 |
+
mpmath==1.3.0
|
44 |
+
networkx==3.3
|
45 |
+
nltk==3.8.1
|
46 |
+
numpy==1.26.1
|
47 |
+
orjson==3.10.3
|
48 |
+
packaging==23.2
|
49 |
+
pandas==2.2.2
|
50 |
+
pillow==10.3.0
|
51 |
+
protobuf==5.27.0
|
52 |
+
pydantic==2.7.2
|
53 |
+
pydantic_core==2.18.3
|
54 |
+
pydub==0.25.1
|
55 |
+
Pygments==2.18.0
|
56 |
+
pyparsing==3.1.2
|
57 |
+
python-dateutil==2.9.0.post0
|
58 |
+
python-dotenv==1.0.1
|
59 |
+
python-multipart==0.0.9
|
60 |
+
pytz==2024.1
|
61 |
+
PyYAML==6.0.1
|
62 |
+
referencing==0.35.1
|
63 |
+
regex==2023.10.3
|
64 |
+
requests==2.31.0
|
65 |
+
rich==13.7.1
|
66 |
+
rpds-py==0.18.1
|
67 |
+
ruff==0.4.6
|
68 |
+
safetensors==0.4.0
|
69 |
+
semantic-version==2.10.0
|
70 |
+
sentencepiece==0.1.99
|
71 |
+
shellingham==1.5.4
|
72 |
+
six==1.16.0
|
73 |
+
sniffio==1.3.1
|
74 |
+
starlette==0.37.2
|
75 |
+
sympy==1.12.1
|
76 |
+
tbb==2021.12.0
|
77 |
+
tokenizers==0.14.1
|
78 |
+
tomlkit==0.12.0
|
79 |
+
toolz==0.12.1
|
80 |
+
torch==2.3.0
|
81 |
+
tqdm==4.66.1
|
82 |
+
transformers==4.34.1
|
83 |
+
typer==0.12.3
|
84 |
+
typing_extensions==4.8.0
|
85 |
+
tzdata==2024.1
|
86 |
+
ujson==5.10.0
|
87 |
+
urllib3==2.0.7
|
88 |
+
uvicorn==0.30.0
|
89 |
+
watchfiles==0.22.0
|
90 |
+
websockets==11.0.3
|
91 |
+
Werkzeug==3.0.1
|
translator.ipynb
ADDED
@@ -0,0 +1,452 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"nbformat": 4,
|
3 |
+
"nbformat_minor": 0,
|
4 |
+
"metadata": {
|
5 |
+
"colab": {
|
6 |
+
"provenance": []
|
7 |
+
},
|
8 |
+
"kernelspec": {
|
9 |
+
"name": "python3",
|
10 |
+
"display_name": "Python 3"
|
11 |
+
},
|
12 |
+
"language_info": {
|
13 |
+
"name": "python"
|
14 |
+
}
|
15 |
+
},
|
16 |
+
"cells": [
|
17 |
+
{
|
18 |
+
"cell_type": "code",
|
19 |
+
"execution_count": null,
|
20 |
+
"metadata": {
|
21 |
+
"colab": {
|
22 |
+
"base_uri": "https://localhost:8080/"
|
23 |
+
},
|
24 |
+
"id": "JW_q5khKnpb7",
|
25 |
+
"outputId": "56c6c160-d1bc-43e1-c25b-677f149e230b"
|
26 |
+
},
|
27 |
+
"outputs": [
|
28 |
+
{
|
29 |
+
"output_type": "stream",
|
30 |
+
"name": "stdout",
|
31 |
+
"text": [
|
32 |
+
"Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.41.1)\n",
|
33 |
+
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.14.0)\n",
|
34 |
+
"Requirement already satisfied: huggingface-hub<1.0,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.23.1)\n",
|
35 |
+
"Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.25.2)\n",
|
36 |
+
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (24.0)\n",
|
37 |
+
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n",
|
38 |
+
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2024.5.15)\n",
|
39 |
+
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n",
|
40 |
+
"Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.19.1)\n",
|
41 |
+
"Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.3)\n",
|
42 |
+
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.4)\n",
|
43 |
+
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.23.0->transformers) (2023.6.0)\n",
|
44 |
+
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.23.0->transformers) (4.11.0)\n",
|
45 |
+
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n",
|
46 |
+
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.7)\n",
|
47 |
+
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n",
|
48 |
+
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.2.2)\n",
|
49 |
+
"Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.23.1)\n",
|
50 |
+
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.14.0)\n",
|
51 |
+
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n",
|
52 |
+
"Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (24.0)\n",
|
53 |
+
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n",
|
54 |
+
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n",
|
55 |
+
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.4)\n",
|
56 |
+
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.11.0)\n",
|
57 |
+
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n",
|
58 |
+
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.7)\n",
|
59 |
+
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n",
|
60 |
+
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2024.2.2)\n"
|
61 |
+
]
|
62 |
+
}
|
63 |
+
],
|
64 |
+
"source": [
|
65 |
+
"!pip install transformers\n",
|
66 |
+
"!pip install huggingface_hub\n",
|
67 |
+
"!python -c \"from huggingface_hub.hf_api import HfFolder; HfFolder.save_token(<YOUR_TOKEN_HERE>)\""
|
68 |
+
]
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"cell_type": "code",
|
72 |
+
"source": [
|
73 |
+
"!pip install sentencepiece\n",
|
74 |
+
"nltk.download('punkt')"
|
75 |
+
],
|
76 |
+
"metadata": {
|
77 |
+
"colab": {
|
78 |
+
"base_uri": "https://localhost:8080/"
|
79 |
+
},
|
80 |
+
"id": "guoGKlR4n1tY",
|
81 |
+
"outputId": "2653425f-2888-4318-cb4f-03a38e805077"
|
82 |
+
},
|
83 |
+
"execution_count": null,
|
84 |
+
"outputs": [
|
85 |
+
{
|
86 |
+
"output_type": "stream",
|
87 |
+
"name": "stdout",
|
88 |
+
"text": [
|
89 |
+
"Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (0.1.99)\n"
|
90 |
+
]
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"output_type": "stream",
|
94 |
+
"name": "stderr",
|
95 |
+
"text": [
|
96 |
+
"[nltk_data] Downloading package punkt to /root/nltk_data...\n",
|
97 |
+
"[nltk_data] Package punkt is already up-to-date!\n"
|
98 |
+
]
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"output_type": "execute_result",
|
102 |
+
"data": {
|
103 |
+
"text/plain": [
|
104 |
+
"True"
|
105 |
+
]
|
106 |
+
},
|
107 |
+
"metadata": {},
|
108 |
+
"execution_count": 30
|
109 |
+
}
|
110 |
+
]
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"cell_type": "code",
|
114 |
+
"source": [
|
115 |
+
"!pip install gradio"
|
116 |
+
],
|
117 |
+
"metadata": {
|
118 |
+
"colab": {
|
119 |
+
"base_uri": "https://localhost:8080/"
|
120 |
+
},
|
121 |
+
"id": "yBUmeZpGo9OX",
|
122 |
+
"outputId": "82e89bb1-c748-4314-899b-4c85bafafa5f"
|
123 |
+
},
|
124 |
+
"execution_count": null,
|
125 |
+
"outputs": [
|
126 |
+
{
|
127 |
+
"output_type": "stream",
|
128 |
+
"name": "stdout",
|
129 |
+
"text": [
|
130 |
+
"Requirement already satisfied: gradio in /usr/local/lib/python3.10/dist-packages (4.32.0)\n",
|
131 |
+
"Requirement already satisfied: aiofiles<24.0,>=22.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (23.2.1)\n",
|
132 |
+
"Requirement already satisfied: altair<6.0,>=4.2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.2.2)\n",
|
133 |
+
"Requirement already satisfied: fastapi in /usr/local/lib/python3.10/dist-packages (from gradio) (0.111.0)\n",
|
134 |
+
"Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio) (0.3.2)\n",
|
135 |
+
"Requirement already satisfied: gradio-client==0.17.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.17.0)\n",
|
136 |
+
"Requirement already satisfied: httpx>=0.24.1 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.27.0)\n",
|
137 |
+
"Requirement already satisfied: huggingface-hub>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.23.1)\n",
|
138 |
+
"Requirement already satisfied: importlib-resources<7.0,>=1.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.4.0)\n",
|
139 |
+
"Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.1.4)\n",
|
140 |
+
"Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.1.5)\n",
|
141 |
+
"Requirement already satisfied: matplotlib~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.7.1)\n",
|
142 |
+
"Requirement already satisfied: numpy~=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.25.2)\n",
|
143 |
+
"Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.10.3)\n",
|
144 |
+
"Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio) (24.0)\n",
|
145 |
+
"Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.0.3)\n",
|
146 |
+
"Requirement already satisfied: pillow<11.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (9.4.0)\n",
|
147 |
+
"Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.7.1)\n",
|
148 |
+
"Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio) (0.25.1)\n",
|
149 |
+
"Requirement already satisfied: python-multipart>=0.0.9 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.0.9)\n",
|
150 |
+
"Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.0.1)\n",
|
151 |
+
"Requirement already satisfied: ruff>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.4.6)\n",
|
152 |
+
"Requirement already satisfied: semantic-version~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.10.0)\n",
|
153 |
+
"Requirement already satisfied: tomlkit==0.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.12.0)\n",
|
154 |
+
"Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.12.3)\n",
|
155 |
+
"Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.11.0)\n",
|
156 |
+
"Requirement already satisfied: urllib3~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.0.7)\n",
|
157 |
+
"Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.30.0)\n",
|
158 |
+
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.17.0->gradio) (2023.6.0)\n",
|
159 |
+
"Requirement already satisfied: websockets<12.0,>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio-client==0.17.0->gradio) (11.0.3)\n",
|
160 |
+
"Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (0.4)\n",
|
161 |
+
"Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (4.19.2)\n",
|
162 |
+
"Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages (from altair<6.0,>=4.2.0->gradio) (0.12.1)\n",
|
163 |
+
"Requirement already satisfied: anyio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (3.7.1)\n",
|
164 |
+
"Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (2024.2.2)\n",
|
165 |
+
"Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (1.0.5)\n",
|
166 |
+
"Requirement already satisfied: idna in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (3.7)\n",
|
167 |
+
"Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (1.3.1)\n",
|
168 |
+
"Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx>=0.24.1->gradio) (0.14.0)\n",
|
169 |
+
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (3.14.0)\n",
|
170 |
+
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (2.31.0)\n",
|
171 |
+
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.19.3->gradio) (4.66.4)\n",
|
172 |
+
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (1.2.1)\n",
|
173 |
+
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (0.12.1)\n",
|
174 |
+
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (4.51.0)\n",
|
175 |
+
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (1.4.5)\n",
|
176 |
+
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (3.1.2)\n",
|
177 |
+
"Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib~=3.0->gradio) (2.8.2)\n",
|
178 |
+
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2023.4)\n",
|
179 |
+
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.1)\n",
|
180 |
+
"Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (0.7.0)\n",
|
181 |
+
"Requirement already satisfied: pydantic-core==2.18.2 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (2.18.2)\n",
|
182 |
+
"Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (8.1.7)\n",
|
183 |
+
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
|
184 |
+
"Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (13.7.1)\n",
|
185 |
+
"Requirement already satisfied: starlette<0.38.0,>=0.37.2 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio) (0.37.2)\n",
|
186 |
+
"Requirement already satisfied: fastapi-cli>=0.0.2 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio) (0.0.4)\n",
|
187 |
+
"Requirement already satisfied: ujson!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,>=4.0.1 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio) (5.10.0)\n",
|
188 |
+
"Requirement already satisfied: email_validator>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from fastapi->gradio) (2.1.1)\n",
|
189 |
+
"Requirement already satisfied: dnspython>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from email_validator>=2.0.0->fastapi->gradio) (2.6.1)\n",
|
190 |
+
"Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (23.2.0)\n",
|
191 |
+
"Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (2023.12.1)\n",
|
192 |
+
"Requirement already satisfied: referencing>=0.28.4 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.35.1)\n",
|
193 |
+
"Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio) (0.18.1)\n",
|
194 |
+
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib~=3.0->gradio) (1.16.0)\n",
|
195 |
+
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
|
196 |
+
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.16.1)\n",
|
197 |
+
"Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio->httpx>=0.24.1->gradio) (1.2.1)\n",
|
198 |
+
"Requirement already satisfied: httptools>=0.5.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio) (0.6.1)\n",
|
199 |
+
"Requirement already satisfied: python-dotenv>=0.13 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio) (1.0.1)\n",
|
200 |
+
"Requirement already satisfied: uvloop!=0.15.0,!=0.15.1,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio) (0.19.0)\n",
|
201 |
+
"Requirement already satisfied: watchfiles>=0.13 in /usr/local/lib/python3.10/dist-packages (from uvicorn>=0.14.0->gradio) (0.22.0)\n",
|
202 |
+
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.19.3->gradio) (3.3.2)\n",
|
203 |
+
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n"
|
204 |
+
]
|
205 |
+
}
|
206 |
+
]
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"cell_type": "code",
|
210 |
+
"source": [
|
211 |
+
"import requests\n",
|
212 |
+
"from transformers import pipeline\n",
|
213 |
+
"import nltk\n",
|
214 |
+
"from nltk import sent_tokenize\n",
|
215 |
+
"from transformers import MBartForConditionalGeneration, MBart50TokenizerFast\n",
|
216 |
+
"from transformers import pipeline"
|
217 |
+
],
|
218 |
+
"metadata": {
|
219 |
+
"id": "laNjJ5sHn7EP"
|
220 |
+
},
|
221 |
+
"execution_count": null,
|
222 |
+
"outputs": []
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"cell_type": "code",
|
226 |
+
"source": [
|
227 |
+
"# Use a pipeline as a high-level helper\n",
|
228 |
+
"from transformers import pipeline\n",
|
229 |
+
"\n",
|
230 |
+
"pipe = pipeline(\"text2text-generation\", model=\"SnypzZz/Llama2-13b-Language-translate\", use_fast = False)"
|
231 |
+
],
|
232 |
+
"metadata": {
|
233 |
+
"id": "GyqW7CypoCsX"
|
234 |
+
},
|
235 |
+
"execution_count": null,
|
236 |
+
"outputs": []
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"cell_type": "code",
|
240 |
+
"source": [
|
241 |
+
"tokenizer = MBart50TokenizerFast.from_pretrained(\"SnypzZz/Llama2-13b-Language-translate\", src_lang=\"en_XX\")\n",
|
242 |
+
"model = None\n",
|
243 |
+
"model_loaded = False"
|
244 |
+
],
|
245 |
+
"metadata": {
|
246 |
+
"id": "XrBJH1-ToJW3"
|
247 |
+
},
|
248 |
+
"execution_count": null,
|
249 |
+
"outputs": []
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"cell_type": "code",
|
253 |
+
"source": [
|
254 |
+
"api_token_header = \"\"\n",
|
255 |
+
"with open('/content/secrets.py', 'r') as f:\n",
|
256 |
+
" api_token_header = f.read()"
|
257 |
+
],
|
258 |
+
"metadata": {
|
259 |
+
"id": "yvoISQtlyyF6"
|
260 |
+
},
|
261 |
+
"execution_count": null,
|
262 |
+
"outputs": []
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"cell_type": "code",
|
266 |
+
"source": [
|
267 |
+
"def load_model():\n",
|
268 |
+
" global model, model_loaded\n",
|
269 |
+
" model = MBartForConditionalGeneration.from_pretrained(\"SnypzZz/Llama2-13b-Language-translate\")\n",
|
270 |
+
" model_loaded =True\n",
|
271 |
+
" return model"
|
272 |
+
],
|
273 |
+
"metadata": {
|
274 |
+
"id": "Z2HyW64woSps"
|
275 |
+
},
|
276 |
+
"execution_count": null,
|
277 |
+
"outputs": []
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"cell_type": "code",
|
281 |
+
"source": [
|
282 |
+
"def translation(text,dest_lang,dest_lang_code, src_lang_code):\n",
|
283 |
+
"\n",
|
284 |
+
" if(dest_lang_code == src_lang_code):\n",
|
285 |
+
" return \"Please select different languages to translate between.\"\n",
|
286 |
+
"\n",
|
287 |
+
" # headers = {\"Authorization\": f\"Bearer {secrets_sih.api_token_header}\"}\n",
|
288 |
+
" headers = {\"Authorization\": f\"Bearer {api_token_header}\"}\n",
|
289 |
+
"\n",
|
290 |
+
" # Bengali Done\n",
|
291 |
+
" if(dest_lang == \"Bengali\" and src_lang_code == \"en_XX\"):\n",
|
292 |
+
" API_URL = \"https://api-inference.huggingface.co/models/csebuetnlp/banglat5_nmt_en_bn\"\n",
|
293 |
+
" def query(payload):\n",
|
294 |
+
" response = requests.post(API_URL, headers=headers, json=payload)\n",
|
295 |
+
" return response.json()\n",
|
296 |
+
" output = query({\n",
|
297 |
+
" \"inputs\": text,\n",
|
298 |
+
" })\n",
|
299 |
+
" print(output)\n",
|
300 |
+
" return output[0]['translation_text']\n",
|
301 |
+
" else:\n",
|
302 |
+
" global model\n",
|
303 |
+
" if model:\n",
|
304 |
+
" pass\n",
|
305 |
+
" else:\n",
|
306 |
+
" model = load_model()\n",
|
307 |
+
" loaded_model = model\n",
|
308 |
+
" tokenizer = MBart50TokenizerFast.from_pretrained(\"SnypzZz/Llama2-13b-Language-translate\", src_lang=src_lang_code)\n",
|
309 |
+
" #model_inputs = tokenizer(text, return_tensors=\"pt\")\n",
|
310 |
+
" loaded_model_inputs = tokenizer(text, return_tensors=\"pt\")\n",
|
311 |
+
"\n",
|
312 |
+
" # translate\n",
|
313 |
+
" generated_tokens = loaded_model.generate(\n",
|
314 |
+
" **loaded_model_inputs,\n",
|
315 |
+
" forced_bos_token_id=tokenizer.lang_code_to_id[dest_lang_code]\n",
|
316 |
+
" )\n",
|
317 |
+
" output = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)\n",
|
318 |
+
" print(output)\n",
|
319 |
+
" return output[0]"
|
320 |
+
],
|
321 |
+
"metadata": {
|
322 |
+
"id": "q2H24G_lobxo"
|
323 |
+
},
|
324 |
+
"execution_count": null,
|
325 |
+
"outputs": []
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"cell_type": "code",
|
329 |
+
"source": [
|
330 |
+
"def main_translation(text,dest_lang_code,src_lang_code):\n",
|
331 |
+
"\n",
|
332 |
+
" codes = {\"en_XX\":\"English\",\"bn_IN\":\"Bengali\", \"en_GB\":\"English\",\"gu_IN\":\"Gujarati\",\"hi_IN\":\"Hindi\",\"ta_IN\":\"Tamil\",\"te_IN\":\"Telugu\",\"mr_IN\":\"Marathi\"}\n",
|
333 |
+
" dest_lang = codes[dest_lang_code]\n",
|
334 |
+
" src_lang = codes[src_lang_code]\n",
|
335 |
+
"\n",
|
336 |
+
" sentences = sent_tokenize(text)\n",
|
337 |
+
" output = \"\"\n",
|
338 |
+
" for line in sentences:\n",
|
339 |
+
" output += translation(line,dest_lang,dest_lang_code, src_lang_code)\n",
|
340 |
+
" return {\"output\":output}"
|
341 |
+
],
|
342 |
+
"metadata": {
|
343 |
+
"id": "Q8-OWT7nodES"
|
344 |
+
},
|
345 |
+
"execution_count": null,
|
346 |
+
"outputs": []
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"cell_type": "code",
|
350 |
+
"source": [
|
351 |
+
"main_translation(\"Hello World\", \"hi_IN\",\"en_XX\")"
|
352 |
+
],
|
353 |
+
"metadata": {
|
354 |
+
"colab": {
|
355 |
+
"base_uri": "https://localhost:8080/"
|
356 |
+
},
|
357 |
+
"id": "EHt29-U2wMp7",
|
358 |
+
"outputId": "c0cd8454-603e-4ed9-919a-cf6801397864"
|
359 |
+
},
|
360 |
+
"execution_count": null,
|
361 |
+
"outputs": [
|
362 |
+
{
|
363 |
+
"output_type": "stream",
|
364 |
+
"name": "stdout",
|
365 |
+
"text": [
|
366 |
+
"['हेलो वर्ल्ड']\n"
|
367 |
+
]
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"output_type": "execute_result",
|
371 |
+
"data": {
|
372 |
+
"text/plain": [
|
373 |
+
"{'output': 'हेलो वर्ल्ड'}"
|
374 |
+
]
|
375 |
+
},
|
376 |
+
"metadata": {},
|
377 |
+
"execution_count": 56
|
378 |
+
}
|
379 |
+
]
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"cell_type": "code",
|
383 |
+
"source": [
|
384 |
+
"#User Interface\n",
|
385 |
+
"\n",
|
386 |
+
"import gradio as gr\n",
|
387 |
+
"\n",
|
388 |
+
"\n",
|
389 |
+
"def test(text, src, dest):\n",
|
390 |
+
" ans = main_translation(text,dest,src)\n",
|
391 |
+
" return ans['output']\n",
|
392 |
+
"demo = gr.Interface(\n",
|
393 |
+
" test,\n",
|
394 |
+
" [\"textbox\",\n",
|
395 |
+
" gr.Dropdown(\n",
|
396 |
+
" [(\"English\", \"en_XX\"), (\"Hindi\",\"hi_IN\"), (\"Bengali\",\"bn_IN\"), (\"Gujarati\",\"gu_IN\"), (\"Tamil\",\"ta_IN\"), (\"Telugu\",\"te_IN\"), (\"Marathi\",\"mr_IN\")], label=\"Source\", info=\"Select the Source Language!\"\n",
|
397 |
+
" ),\n",
|
398 |
+
" gr.Dropdown(\n",
|
399 |
+
" [(\"English\", \"en_XX\"), (\"Hindi\",\"hi_IN\"), (\"Bengali\",\"bn_IN\"), (\"Gujarati\",\"gu_IN\"), (\"Tamil\",\"ta_IN\"), (\"Telugu\",\"te_IN\"), (\"Marathi\",\"mr_IN\")], label=\"Destination\", info=\"Select the Destination Language!\"\n",
|
400 |
+
" ),\n",
|
401 |
+
" ],\n",
|
402 |
+
" outputs=[\"textbox\"],\n",
|
403 |
+
")\n",
|
404 |
+
"\n",
|
405 |
+
"demo.launch()\n"
|
406 |
+
],
|
407 |
+
"metadata": {
|
408 |
+
"colab": {
|
409 |
+
"base_uri": "https://localhost:8080/",
|
410 |
+
"height": 646
|
411 |
+
},
|
412 |
+
"id": "ebFtlmmmpCQO",
|
413 |
+
"outputId": "a064cd8e-dca3-4eda-d95e-bc25fac28d23"
|
414 |
+
},
|
415 |
+
"execution_count": null,
|
416 |
+
"outputs": [
|
417 |
+
{
|
418 |
+
"output_type": "stream",
|
419 |
+
"name": "stdout",
|
420 |
+
"text": [
|
421 |
+
"Setting queue=True in a Colab notebook requires sharing enabled. Setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
|
422 |
+
"\n",
|
423 |
+
"Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
|
424 |
+
"Running on public URL: https://3800d81e3201b8d734.gradio.live\n",
|
425 |
+
"\n",
|
426 |
+
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
|
427 |
+
]
|
428 |
+
},
|
429 |
+
{
|
430 |
+
"output_type": "display_data",
|
431 |
+
"data": {
|
432 |
+
"text/plain": [
|
433 |
+
"<IPython.core.display.HTML object>"
|
434 |
+
],
|
435 |
+
"text/html": [
|
436 |
+
"<div><iframe src=\"https://3800d81e3201b8d734.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
|
437 |
+
]
|
438 |
+
},
|
439 |
+
"metadata": {}
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"output_type": "execute_result",
|
443 |
+
"data": {
|
444 |
+
"text/plain": []
|
445 |
+
},
|
446 |
+
"metadata": {},
|
447 |
+
"execution_count": 57
|
448 |
+
}
|
449 |
+
]
|
450 |
+
}
|
451 |
+
]
|
452 |
+
}
|