prabodbc commited on
Commit
9d14cb7
·
verified ·
1 Parent(s): 4e415ce

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -22,6 +22,13 @@ for fast local transcription on Apple Silicon.
22
  | File | Precision | Size |
23
  |------|-----------|------|
24
  | `whisper-large-v2-F16.base` | float16 | 3.10 GB |
 
 
 
 
 
 
 
25
 
26
  ## Usage
27
 
 
22
  | File | Precision | Size |
23
  |------|-----------|------|
24
  | `whisper-large-v2-F16.base` | float16 | 3.10 GB |
25
+ | `whisper-large-v2-Q8.base` | 8-bit linears, f16 embeddings/conv/norms | 1.68 GB |
26
+ | `whisper-large-v2-Q4.base` | 4-bit linears, f16 embeddings/conv/norms | 987 MB |
27
+
28
+ F16 and Q8 are transcription-quality equivalent (Q8 passes the same
29
+ word-error parity gates against reference openai-whisper). Q4 is the
30
+ smallest and remains accurate; on some smaller variants it can
31
+ occasionally repeat a word in timestamped beam decoding.
32
 
33
  ## Usage
34