Chillarmo
/

ATOM

Automatic Speech Recognition

morpheme-tokenization

Generated from Trainer

Model card Files Files and versions

Chillarmo commited on Nov 24, 2025

Commit

7d6f07d

·

verified ·

1 Parent(s): 7d29826

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ model-index:
       split: test
     metrics:
     - type: wer
-      value: 42.1
       name: Word Error Rate
     - type: exact_match
       value: 10.06
@@ -78,7 +78,7 @@ Evaluated on Common Voice 20.0 Armenian test set:
 | Whisper-medium | 769M | 60.1%* | +49.3% |
 | Whisper-large | 1550M | 53.7%* | +54.7% |
 | Whisper-large-v2 | 1550M | 44.6%* | +62.4% |
-| **ATOM** | **28M** | **42.1%** | **+64.5%** ✅ |
 *Whisper WER values for Armenian from published benchmarks

       split: test
     metrics:
     - type: wer
+      value: 50.3
       name: Word Error Rate
     - type: exact_match
       value: 10.06
 | Whisper-medium | 769M | 60.1%* | +49.3% |
 | Whisper-large | 1550M | 53.7%* | +54.7% |
 | Whisper-large-v2 | 1550M | 44.6%* | +62.4% |
+| **ATOM** | **14M** | **50.3%** | **+57.6%** ✅ |
 *Whisper WER values for Armenian from published benchmarks