mlboydaisuke commited on
Commit
63856c4
·
verified ·
1 Parent(s): 376b15b

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +8 -0
README.md CHANGED
@@ -62,6 +62,14 @@ exported both ways, whisper-tiny's decoder comes out at 198.0 MB exactly.
62
 
63
 
64
 
 
 
 
 
 
 
 
 
65
  ## Conversion
66
 
67
  ```bash
 
62
 
63
 
64
 
65
+ ### Checked in the task's own units
66
+
67
+ Correlation is a first filter. These are the numbers that decide:
68
+
69
+ - **encoder int8** — measured end to end — word error rate against the fp32 encoder: mean WER 0.0% (worst clip 0.0%) over 5 spoken sentences, int8 encoder against the fp32 encoder with the same fp32 decoder and the same waveform; the fp32 arm transcribes all five correctly, so the comparison is against a working control rather than against noise.
70
+
71
+ The sensitivity of that test, measured by injecting random noise into whisper-tiny's encoder output: rel_l2 0.03 (what int8 actually costs) and 0.10 both give WER 0.000; 0.20 and 0.40 give 0.025. Five clean sentences leave headroom, so a pass means *does not break the transcript*, not *indistinguishable at any error level*.
72
+
73
  ## Conversion
74
 
75
  ```bash