Upload 7 files

README.md.txt

@@ -0,0 +1,39 @@
+---
+language: 
+  - en
+  - te
+tags:
+  - translation
+  - machine-translation
+  - NLP
+  - pytorch
+license: "MIT"
+datasets:
+  - hima06varshini/english-telugu-parallel-corpus
+widget:
+  - text: "Hello, how are you?"
+---
+
+# 🏆 English-to-Telugu Translation Model
+
+This model translates **English** text into **Telugu** using a Transformer-based approach.
+
+## 📂 Model Details
+- **Model Name**: `hima06varshini/english-to-telugu-translation`
+- **Developed by**: Y. Himavarshini
+- **License**: MIT License
+
+## 🚀 Usage
+```python
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+model_name = "hima06varshini/english-to-telugu-translation"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+def translate(text):
+    inputs = tokenizer(text, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+print(translate("Hello, how are you?"))

config.json

@@ -0,0 +1,9 @@
+{
+  "model_type": "transformer",
+  "num_layers": 6,
+  "hidden_size": 512,
+  "vocab_size": 32000,
+  "max_position_embeddings": 512,
+  "attention_heads": 8,
+  "dropout_rate": 0.1
+}

inference.py

@@ -0,0 +1,16 @@
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+# Load model and tokenizer
+model_name = "hima06varshini/english-to-telugu-translation"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+def translate(text):
+    inputs = tokenizer(text, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Example usage
+text = "Hello, how are you?"
+translation = translate(text)
+print("Translated text:", translation)

model_card.yaml.txt

@@ -0,0 +1,48 @@
+model_name: "english-to-telugu-translation"
+tags:
+  - translation
+  - machine-translation
+  - english
+  - telugu
+library_name: "transformers"
+license: "MIT"
+language: 
+  - en
+  - te
+metrics:
+  - "BLEU"
+  - "ROUGE"
+  - "METEOR"
+model_description: |
+  This model is trained for English-to-Telugu translation using a Transformer-based architecture.
+  It is fine-tuned on a large parallel dataset of English and Telugu sentences.
+
+source: "Trained on the English-Telugu Parallel Corpus dataset."
+citation: |
+  If you use this model, please cite:
+  "English-to-Telugu Translation Model, created by Y. Himavarshini, 2025"
+  
+model_creators:
+  - "Y. Himavarshini"
+  - "Gates Institute of Technology"
+
+task_categories:
+  - "Machine Translation"
+
+task_ids:
+  - "translation"
+
+pretty_name: "English-to-Telugu Translation Model"
+
+model_config:
+  architecture: "Transformer"
+  num_layers: 6
+  hidden_size: 512
+  vocab_size: 32000
+
+datasets:
+  - "hima06varshini/english-telugu-parallel-corpus"
+
+inference_example:
+  - input: "Hello, how are you?"
+    output: "హలో, మీరు ఎలా ఉన్నారు?"

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734b5556bf566636ee967fca37c75cc40dc3c6ea048cc6ea89e0f496f07fcbad
+size 109

tokenizer.json

@@ -0,0 +1,4 @@
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("your-model-name")
+tokenizer.save_pretrained("model_directory")

vocab.txt

@@ -0,0 +1,3 @@
+with open("vocab.txt", "w") as f:
+    for token in tokenizer.get_vocab().keys():
+        f.write(token + "\n")