Automatic Speech Recognition
PEFT
Safetensors
German
Swiss German
whisper
swiss-german
dialect
asr
speech-recognition
lora
fine-tuned
Eval Results (legacy)
Instructions to use Flix-AI/flix-swissgerman-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Flix-AI/flix-swissgerman-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("openai/whisper-large-v3") model = PeftModel.from_pretrained(base_model, "Flix-AI/flix-swissgerman-lora") - Notebooks
- Google Colab
- Kaggle
Rename model: swiss-german → swissgerman
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ base_model: openai/whisper-large-v3
|
|
| 17 |
datasets:
|
| 18 |
- i4ds/spc_r
|
| 19 |
model-index:
|
| 20 |
-
- name: flix-
|
| 21 |
results:
|
| 22 |
- task:
|
| 23 |
type: automatic-speech-recognition
|
|
@@ -36,7 +36,7 @@ model-index:
|
|
| 36 |
name: WER
|
| 37 |
---
|
| 38 |
|
| 39 |
-
# flix-
|
| 40 |
|
| 41 |
A LoRA adapter for [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) fine-tuned for Swiss German (Schweizerdeutsch) automatic speech recognition. The adapter transcribes Swiss German dialect speech into grammatically correct Standard German text.
|
| 42 |
|
|
@@ -76,7 +76,7 @@ from peft import PeftModel
|
|
| 76 |
import torch
|
| 77 |
|
| 78 |
base_model_id = "openai/whisper-large-v3"
|
| 79 |
-
adapter_id = "Flix-AI/flix-
|
| 80 |
|
| 81 |
processor = WhisperProcessor.from_pretrained(base_model_id)
|
| 82 |
model = WhisperForConditionalGeneration.from_pretrained(
|
|
@@ -161,7 +161,7 @@ The training data covers all major Swiss German dialect regions:
|
|
| 161 |
title={Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6\% WER (13.8\% cWER)},
|
| 162 |
author={Akeret, Felix},
|
| 163 |
year={2026},
|
| 164 |
-
url={https://huggingface.co/Flix-AI/flix-
|
| 165 |
}
|
| 166 |
```
|
| 167 |
|
|
|
|
| 17 |
datasets:
|
| 18 |
- i4ds/spc_r
|
| 19 |
model-index:
|
| 20 |
+
- name: flix-swissgerman-lora
|
| 21 |
results:
|
| 22 |
- task:
|
| 23 |
type: automatic-speech-recognition
|
|
|
|
| 36 |
name: WER
|
| 37 |
---
|
| 38 |
|
| 39 |
+
# flix-swissgerman-lora
|
| 40 |
|
| 41 |
A LoRA adapter for [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) fine-tuned for Swiss German (Schweizerdeutsch) automatic speech recognition. The adapter transcribes Swiss German dialect speech into grammatically correct Standard German text.
|
| 42 |
|
|
|
|
| 76 |
import torch
|
| 77 |
|
| 78 |
base_model_id = "openai/whisper-large-v3"
|
| 79 |
+
adapter_id = "Flix-AI/flix-swissgerman-lora"
|
| 80 |
|
| 81 |
processor = WhisperProcessor.from_pretrained(base_model_id)
|
| 82 |
model = WhisperForConditionalGeneration.from_pretrained(
|
|
|
|
| 161 |
title={Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6\% WER (13.8\% cWER)},
|
| 162 |
author={Akeret, Felix},
|
| 163 |
year={2026},
|
| 164 |
+
url={https://huggingface.co/Flix-AI/flix-swissgerman-lora}
|
| 165 |
}
|
| 166 |
```
|
| 167 |
|