---
license: bigscience-openrail-m
datasets:
- openai/gdpval
language:
- af
metrics:
- character
base_model:
- sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
new_version: deepseek-ai/DeepSeek-OCR
pipeline_tag: voice-activity-detection
library_name: diffusers
tags:
- art
- agent
---
---# install
pip install transformers datasets accelerate

# training (very simplified)
python run_speech_to_text_flax.py \
  --model_name_or_path openai/whisper-small \
  --train_data_dir ./chichewa_speech/train \
  --validation_data_dir ./chichewa_speech/val \
  --output_dir ./whisper-chichewa-finetuned
license: bigscience-openrail-m
datasets:
- openai/gdpval
language:
- af
metrics:
- character
base_model:
- deepseek-ai/DeepSeek-OCR
new_version: zai-org/GLM-4.6
pipeline_tag: translation
library_name: adapter-transformers
tags:
- art
---
GPT2from transformers import MarianTokenizer, MarianMTModel
model = MarianMTModel.from_pretrained("your-org/marian-chichewa-en")
tok = MarianTokenizer.from_pretrained("your-org/marian-chichewa-en")
batch = tok(["Muli bwanji?"], return_tensors="pt", padding=True)
out = model.generate(**batch)
print(tok.batch_decode(out, skip_special_tokens=True))