Flix-AI commited on
Commit
e9e825e
·
verified ·
1 Parent(s): a2b347c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +33 -28
README.md CHANGED
@@ -1,39 +1,39 @@
1
  ---
2
  language:
3
- - de
4
- - gsw
5
  license: apache-2.0
6
  library_name: peft
7
  pipeline_tag: automatic-speech-recognition
8
  tags:
9
- - whisper
10
- - swiss-german
11
- - dialect
12
- - asr
13
- - speech-recognition
14
- - lora
15
- - fine-tuned
16
  base_model: openai/whisper-large-v3
17
  datasets:
18
- - i4ds/spc_r
19
  model-index:
20
- - name: flix-swissgerman-lora
21
- results:
22
- - task:
23
- type: automatic-speech-recognition
24
- name: Speech Recognition
25
- dataset:
26
- type: custom
27
- name: ASGDTS (All Swiss German Dialects Test Set)
28
- config: 200-sample subset
29
- split: test
30
- args:
31
- samples: 200
32
- seed: 42
33
- metrics:
34
- - type: wer
35
- value: 25.32
36
- name: WER
37
  ---
38
 
39
  # flix-swissgerman-lora
@@ -42,6 +42,8 @@ A LoRA adapter for [openai/whisper-large-v3](https://huggingface.co/openai/whisp
42
 
43
  **This is among the first publicly available, honestly evaluated LoRA adapters for Swiss German ASR.**
44
 
 
 
45
  ## Model Description
46
 
47
  - **Base model:** openai/whisper-large-v3 (1.55B parameters)
@@ -161,7 +163,10 @@ 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-swissgerman-lora}
 
 
 
165
  }
166
  ```
167
 
 
1
  ---
2
  language:
3
+ - de
4
+ - gsw
5
  license: apache-2.0
6
  library_name: peft
7
  pipeline_tag: automatic-speech-recognition
8
  tags:
9
+ - whisper
10
+ - swiss-german
11
+ - dialect
12
+ - asr
13
+ - speech-recognition
14
+ - lora
15
+ - fine-tuned
16
  base_model: openai/whisper-large-v3
17
  datasets:
18
+ - i4ds/spc_r
19
  model-index:
20
+ - name: flix-swissgerman-lora
21
+ results:
22
+ - task:
23
+ type: automatic-speech-recognition
24
+ name: Speech Recognition
25
+ dataset:
26
+ name: ASGDTS (All Swiss German Dialects Test Set)
27
+ type: custom
28
+ config: 200-sample subset
29
+ split: test
30
+ args:
31
+ samples: 200
32
+ seed: 42
33
+ metrics:
34
+ - type: wer
35
+ value: 25.32
36
+ name: WER
37
  ---
38
 
39
  # flix-swissgerman-lora
 
42
 
43
  **This is among the first publicly available, honestly evaluated LoRA adapters for Swiss German ASR.**
44
 
45
+ 📄 **Paper:** [https://arxiv.org/abs/2606.07608](https://arxiv.org/abs/2606.07608)
46
+
47
  ## Model Description
48
 
49
  - **Base model:** openai/whisper-large-v3 (1.55B parameters)
 
163
  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)},
164
  author={Akeret, Felix},
165
  year={2026},
166
+ url={https://arxiv.org/abs/2606.07608},
167
+ eprint={2606.07608},
168
+ archivePrefix={arXiv},
169
+ primaryClass={cs.CL}
170
  }
171
  ```
172