| --- |
| language: |
| - hi |
| - en |
| license: apache-2.0 |
| library_name: sentence-transformers |
| tags: |
| - sentence-transformers |
| - feature-extraction |
| - hindi |
| - hinglish |
| - code-mixed |
| - song-lyrics |
| - tsdae |
| base_model: AkshitaS/bhasha-embed-v0 |
| --- |
| |
| # BhashaEmbed Hindi Songs — TSDAE Domain Adapted |
|
|
| Domain-adapted version of [`AkshitaS/bhasha-embed-v0`](https://huggingface.co/AkshitaS/bhasha-embed-v0) |
| for Hindi film song lyrics. |
|
|
| ## Training |
|
|
| - **Method:** TSDAE full fine-tuning (no quantization, no LoRA) |
| - **Fine-tuning:** Full parameter fine-tuning (all weights updated) |
| - **Corpus:** 8,464 Hindi film songs, 28,713 verse-level chunks |
| - **Scripts:** Devanagari, Romanized Hindi (Hinglish), English — single unified model |
| - **Script balancing:** weighted sampling to 44/44/12 (Devanagari/Hinglish/English) |
| - **Epochs:** 5 |
| - **Batch size:** 4 |
| - **Learning rate:** 3e-05 |
| - **Max sequence length:** 400 subword tokens |
|
|
| ## Intended Use |
|
|
| Sentence embeddings for Hindi film song lyrics across all three script forms. |
| Designed for thematic classification and generational/temporal analysis of Hindi music. |
|
|
| ## Limitations |
|
|
| - Full parameter fine-tuning — no LoRA/quantization constraints on how far |
| weights can move from the base model |
| - No supervised thematic fine-tuning applied (Phase A only) |
| - Not evaluated on tasks outside Hindi song lyrics |
|
|
| ## Usage |
|
|
| ```python |
| from sentence_transformers import SentenceTransformer |
| |
| model = SentenceTransformer("meet5568/bhash_finetune") |
| |
| lyrics = [ |
| "तेरे बिना जिंदगी से कोई शिकवा नहीं", |
| "tere bina zindagi se koi shikwa nahi", |
| "without you life has no complaint", |
| ] |
| embeddings = model.encode(lyrics) |
| print(embeddings.shape) # (3, 768) |
| ``` |
|
|
