You can deploy this model and start earning money today!

ValleHorn/
german-audio-correction-gemma2

Name: german-audio-correction-gemma2
Rating: 2.5 (117 reviews)

Views

No views yet

Model Card for Model ID

license: apache-2.0 base_model: unsloth/gemma-2-2b-it tags:

fine-tuned
text-correction
german
asr-postprocessing
gguf
unsloth
lora

German Audio Correction - Gemma-2-2B-IT Fine-Tune

Overview

This model is a fine-tuned version of unsloth/gemma-2-2b-it, specialized for correcting German text from audio transcriptions (STT/ASR outputs). It fixes phonetic errors (e.g., misheard words), awkward sentence structures, repetitions (e.g., "die die"), and punctuation issues while preserving the original meaning. Designed for chaining after an STT model like Whisper, it helps create clean, readable German text for applications like note-taking or web apps.

Background: Proprietary APIs (e.g., OpenAI) offer quick inference but limit control. This open-source fine-tune runs locally (e.g., on laptops with 32GB RAM via Ollama/GGUF) or via HF, allowing customization and offline use.

Base Model

Original: unsloth/gemma-2-2b-it (2B parameters, instruct-tuned for tasks like generation/editing; quantized to 4-bit for efficiency).
Architecture: Gemma-2 (Google's lightweight transformer variant, optimized for speed on consumer hardware).

Fine-Tuning Details

Dataset: Custom JSONL (~200 pairs of noisy/clean German texts, user-generated from audio scenarios—e.g., {"prompt": "ich habe das Ticket erstellt; die die also Nummer ahm genau ist SUP-5555.", "response": "Ich habe das Ticket erstellt; die Nummer ist SUP-5555."}).
Method: LoRA (Parameter-Efficient Fine-Tuning) with r=16, lora_alpha=32, target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"], dropout=0.05, via Unsloth for 2x faster training on quantized models.
Training: 200 steps, effective batch size=16 (per_device=4, accumulation=4), learning_rate=2e-4, optimizer=adamw_8bit, on Colab T4 GPU. No eval set (small dataset); monitored via loss logs.
Quantization: Exported as Q4_K_M GGUF (~1.5GB) for local inference (balances quality/speed; runs on CPU/GPU).
Hardware: Tested on ASUS Zenbook (Ryzen 9, 32GB RAM) for local runs.

Usage

Local Inference with Ollama

Pull: ollama pull vallehorn/german-audio-correction-gemma2:q4_k_m
Run: ollama run vallehorn/german-audio-correction-gemma2
Prompt example: "ich habe das Ticket erstellt; die die also Nummer ahm genau ist SUP-5555."
Expected output: "Ich habe das Ticket erstellt; die Nummer ist SUP-5555."

Use the Modelfile for custom params (e.g., temperature=0.7).

Python Inference (via Unsloth/HF)

python

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained("ValleHorn/german-audio-correction-gemma2")
model = FastLanguageModel.for_inference(model)

messages = [{"role": "user", "content": "Noisy German text here"}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids=inputs, max_new_tokens=128, temperature=0.7)
print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))