Upload 2 files

README.md

@@ -1,3 +1,66 @@
 ---
 license: apache-2.0
+datasets:
+  - google/fleurs
+  - mozilla-foundation/common_voice_16_1
+  - vivos
+  - doof-ferb/vlsp2020_vinai_100h
+  - doof-ferb/fpt_fosd
+  - doof-ferb/infore1_25hours
+language: ["vi"]
+library_name: peft
+base_model: openai/whisper-large-v3
+pipeline_tag: automatic-speech-recognition
+metrics: ["wer"]
+model-index:
+- name: doof-ferb/whisper-large-peft-lora-vi
+  results:
+  - task:
+      type: automatic-speech-recognition
+    dataset:
+      type: mozilla-foundation/common_voice_16_1
+      name: Mozilla CommonVoice (Vietnamese) v16.1
+      config: vi
+      split: test
+    metrics:
+      - type: wer
+        value: 14.7
+        verified: false
+  - task:
+      type: automatic-speech-recognition
+    dataset:
+      type: google/fleurs
+      name: Google FLEURS (Vietnamese)
+      config: vi_vn
+      split: test
+    metrics:
+      - type: wer
+        value: 14.7
+        verified: false
+  - task:
+      type: automatic-speech-recognition
+    dataset:
+      type: vivos
+      name: ĐHQG TPHCM VIVOS
+      split: test
+    metrics:
+      - type: wer
+        value: 9.4
+        verified: false
 ---
+
+whisper large v3 PEFT LoRA trained on a big collection of vietnamese speech datasets
+
+TODO:
+- [x] training then publish checkpoint
+- [x] evaluate WER on Common Voice & FLEURS & VIVOS
+
+3.6k steps, warm-up 5%, batch size 16×2 (kaggle free T4×2), train 3.6% of 1.6B params
+
+manually evaluate WER on test set - vietnamese part:
+| @ `float16` | `CommonVoice v16.1` | `FLEURS` | `VIVOS` |
+|---|---|---|---|
+| original `whisper-large-v3` | 16.2% | 8.3% | 12.3% |
+| this LoRA | 14.7% | 14.7% | 9.4% |
+
+all training + evaluation scripts are on my repo: https://github.com/phineas-pta/fine-tune-whisper-vi

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546e6e9c898614b57ae3138af92f2d2a5eb3f74cde443d8b0cbd1ff0fe1f372b
+size 4920