asahi417 commited on
Commit
703a868
·
verified ·
1 Parent(s): 1cdde27

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -54,6 +54,11 @@ We measure the inference speed of different kotoba-whisper-v1.0 implementations
54
  |audio 3 | 4.9 | 30 | 141 | |
55
  |audio 4 | 5.6 | 35 | 126 | |
56
 
 
 
 
 
 
57
 
58
  ### Quantized Model
59
  To use the quantized model, download the quantized GGML weights:
 
54
  |audio 3 | 4.9 | 30 | 141 | |
55
  |audio 4 | 5.6 | 35 | 126 | |
56
 
57
+ Scripts to re-run the experiment can be found bellow:
58
+ * [whisper.cpp](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-ggml): [https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-ggml/blob/main/benchmark.sh](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-ggml/blob/main/benchmark.sh)
59
+ * [faster-whisper](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-faster): [https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-faster/blob/main/benchmark.sh](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-faster/blob/main/benchmark.sh)
60
+ * [hf pipeline](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0): [https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0/blob/main/benchmark.sh](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0/blob/main/benchmark.sh)
61
+
62
 
63
  ### Quantized Model
64
  To use the quantized model, download the quantized GGML weights: