aotrih commited on
Commit
9c2558a
β€’
1 Parent(s): 245dbee

whisperkittools generated README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -28
README.md CHANGED
@@ -10,43 +10,48 @@ tags:
10
  - asr
11
  - quantized
12
  ---
13
- # WhisperKit Evaluation Results
14
 
15
 
16
 
17
  ## Dataset: `librispeech`
18
  Short-form Audio (<30s/clip) - 5 hours of English audiobook clips
19
 
20
- | | WER (↓) | QoI (↑) | File Size (MB) | Code Commit |
21
- |:--------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------|----------:|-----------------:|:--------------|
22
- | WhisperOpenAIAPI/openai_whisper-large-v2 | [2.35](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperOpenAIAPI/openai_whisper-large-v2/librispeech) | 100 | 3100 | N/A |
23
- | [WhisperKit/openai_whisper-large-v3](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3) | [2.04](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3/librispeech) | 95.2 | 3100 | 2846fd9 |
24
- | [WhisperKit/openai_whisper-large-v3_turbo](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3_turbo) | [2.03](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3_turbo/librispeech) | 95.4 | 3100 | 2846fd9 |
25
- | [WhisperKit/openai_whisper-large-v3_turbo_1018MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3_turbo_1018MB) | [1.99](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3_turbo_1018MB/librispeech) | 94.8 | 1018 | 2846fd9 |
26
- | [WhisperKit/openai_whisper-large-v2](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v2) | [2.77](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v2/librispeech) | 96.6 | 3100 | 2846fd9 |
27
- | [WhisperKit/openai_whisper-large-v2_1050MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v2_1050MB) | [2.81](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v2_1050MB/librispeech) | 95 | 1050 | 2846fd9 |
28
- | [WhisperKit/openai_whisper-large-v2_turbo](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v2_turbo) | [2.76](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v2_turbo/librispeech) | 96.6 | 3100 | 2846fd9 |
29
- | [WhisperKit/openai_whisper-large-v2_turbo_1022MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v2_turbo_1022MB) | [2.66](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v2_turbo_1022MB/librispeech) | 94.9 | 1022 | 2846fd9 |
30
- | [WhisperKit/openai_whisper-small.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-small.en) | [3.12](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-small.en/librispeech) | 85.8 | 483 | 228630c |
31
- | [WhisperKit/openai_whisper-small](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-small) | [3.45](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-small/librispeech) | 83 | 483 | 228630c |
32
- | [WhisperKit/openai_whisper-base.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-base.en) | [3.98](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-base.en/librispeech) | 75.3 | 145 | 228630c |
33
- | [WhisperKit/openai_whisper-base](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-base) | [4.97](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-base/librispeech) | 67.2 | 145 | 228630c |
34
- | [WhisperKit/openai_whisper-tiny.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-tiny.en) | [5.61](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-tiny.en/librispeech) | 63.9 | 66 | 228630c |
35
- | [WhisperKit/openai_whisper-tiny](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-tiny) | [7.47](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-tiny/librispeech) | 52.5 | 66 | 228630c |
36
- | whisper.cpp/openai_whisper-large-v3 | [1.97](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/whisper.cpp/openai_whisper-large-v3/librispeech) | 95.4 | 3100 | 25d313b |
 
 
 
 
37
 
38
  ## Dataset: `earnings22`
39
  Long-Form Audio (>1hr/clip) - 120 hours of earnings call recordings in English with various accents
40
 
41
- | | WER (↓) | QoI (↑) | File Size (MB) | Code Commit |
42
- |:------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|----------:|-----------------:|:--------------|
43
- | WhisperOpenAIAPI/openai_whisper-large-v2 | [16.27](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperOpenAIAPI/openai_whisper-large-v2/earnings22) | 100 | 3100 | N/A |
44
- | [WhisperKit/openai_whisper-large-v3](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3) | [15.17](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3/earnings22) | 58.5 | 3100 | 2846fd9 |
45
- | [WhisperKit/openai_whisper-base.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-base.en) | [23.49](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-base.en/earnings22) | 6.5 | 145 | dda6571 |
46
- | [WhisperKit/openai_whisper-tiny.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-tiny.en) | [28.64](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-tiny.en/earnings22) | 5.7 | 66 | dda6571 |
47
- | whisper.cpp/openai_whisper-large-v3 | [33.58](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/whisper.cpp/openai_whisper-large-v3/earnings22) | 6.5 | 3100 | 25d313b |
48
 
49
 
 
 
50
  We believe that rigorously measuring the quality of inference is necessary for developers and
51
  enterprises to make informed decisions when opting to use optimized or compressed variants of
52
  any machine learning model in production. To contextualize `WhisperKit`, we take the following Whisper
@@ -91,11 +96,11 @@ the tooling necessary to run the same measurements on such custom test sets, ple
91
  - [earnings22](https://huggingface.co/datasets/argmaxinc/earnings22): ~120 hours of English audio clips from earnings calls with various accents, tests long-form transcription quality
92
 
93
  ### Reproducing Results
94
- Results in this page are generated by our cluster of Apple Silicon Macs. We use them as self-hosted runners on
95
- Github Actions as our CI infrastructure. Due to [security concerns](https://docs.github.com/en/actions/security-guides/security-hardening-for-github-actions#hardening-for-self-hosted-runners),
96
  we are unable to open up the cluster to the public. However, any Apple Silicon Mac (even with 8GB RAM) can be used to
97
  run identical [evaluation jobs](#evaluation) locally. For reference, our M2 Ultra devices complete a `librispeech` + `openai/whisper-large-v3`
98
- evaluation in under 1 hour regardless of the Whisper implementation. Older Apple Silicon Macs should take less than 1 day to complete the same evaluation.
99
 
100
 
101
 
 
10
  - asr
11
  - quantized
12
  ---
13
+ # Whisper Transcription Quality
14
 
15
 
16
 
17
  ## Dataset: `librispeech`
18
  Short-form Audio (<30s/clip) - 5 hours of English audiobook clips
19
 
20
+ | | WER (↓) | QoI (↑) | File Size (MB) | Code Commit |
21
+ |:--------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------|----------:|-----------------:|:---------------------------------------------------------------|
22
+ | WhisperOpenAIAPI/openai_whisper-large-v2 | [2.35](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperOpenAIAPI/openai_whisper-large-v2/librispeech) | 100 | 3100 | N/A |
23
+ | [WhisperKit/openai_whisper-large-v2](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v2) | [2.77](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v2/librispeech) | 96.6 | 3100 | [Link](https://github.com/argmaxinc/WhisperKit/commit/2846fd9) |
24
+ | [WhisperKit/openai_whisper-large-v2_949MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v2_949MB) | [2.4](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v2_949MB/librispeech) | 94.6 | 949 | [Link](https://github.com/argmaxinc/WhisperKit/commit/eca4a2e) |
25
+ | [WhisperKit/openai_whisper-large-v2_turbo](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v2_turbo) | [2.76](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v2_turbo/librispeech) | 96.6 | 3100 | [Link](https://github.com/argmaxinc/WhisperKit/commit/2846fd9) |
26
+ | [WhisperKit/openai_whisper-large-v2_turbo_955MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v2_turbo_955MB) | [2.41](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v2_turbo_955MB/librispeech) | 94.6 | 955 | [Link](https://github.com/argmaxinc/WhisperKit/commit/cf75348) |
27
+ | [WhisperKit/openai_whisper-large-v3](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3) | [2.04](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3/librispeech) | 95.2 | 3100 | [Link](https://github.com/argmaxinc/WhisperKit/commit/2846fd9) |
28
+ | [WhisperKit/openai_whisper-large-v3_947MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3_947MB) | [2.46](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3_947MB/librispeech) | 93.9 | 947 | [Link](https://github.com/argmaxinc/WhisperKit/commit/eca4a2e) |
29
+ | [WhisperKit/openai_whisper-large-v3_turbo](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3_turbo) | [2.03](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3_turbo/librispeech) | 95.4 | 3100 | [Link](https://github.com/argmaxinc/WhisperKit/commit/2846fd9) |
30
+ | [WhisperKit/openai_whisper-large-v3_turbo_954MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3_turbo_954MB) | [2.47](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3_turbo_954MB/librispeech) | 93.9 | 954 | [Link](https://github.com/argmaxinc/WhisperKit/commit/cf75348) |
31
+ | [WhisperKit/distil-whisper_distil-large-v3](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/distil-whisper_distil-large-v3) | [2.47](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/distil-whisper_distil-large-v3/librispeech) | 89.7 | 1510 | [Link](https://github.com/argmaxinc/WhisperKit/commit/cf75348) |
32
+ | [WhisperKit/distil-whisper_distil-large-v3_594MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/distil-whisper_distil-large-v3_594MB) | [2.96](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/distil-whisper_distil-large-v3_594MB/librispeech) | 85.4 | 594 | [Link](https://github.com/argmaxinc/WhisperKit/commit/508240f) |
33
+ | [WhisperKit/distil-whisper_distil-large-v3_turbo](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/distil-whisper_distil-large-v3_turbo) | [2.47](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/distil-whisper_distil-large-v3_turbo/librispeech) | 89.7 | 1510 | [Link](https://github.com/argmaxinc/WhisperKit/commit/508240f) |
34
+ | [WhisperKit/distil-whisper_distil-large-v3_turbo_600MB](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/distil-whisper_distil-large-v3_turbo_600MB) | [2.78](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/distil-whisper_distil-large-v3_turbo_600MB/librispeech) | 86.2 | 600 | [Link](https://github.com/argmaxinc/WhisperKit/commit/ae1cf96) |
35
+ | [WhisperKit/openai_whisper-small.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-small.en) | [3.12](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-small.en/librispeech) | 85.8 | 483 | [Link](https://github.com/argmaxinc/WhisperKit/commit/228630c) |
36
+ | [WhisperKit/openai_whisper-small](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-small) | [3.45](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-small/librispeech) | 83 | 483 | [Link](https://github.com/argmaxinc/WhisperKit/commit/228630c) |
37
+ | [WhisperKit/openai_whisper-base.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-base.en) | [3.98](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-base.en/librispeech) | 75.3 | 145 | [Link](https://github.com/argmaxinc/WhisperKit/commit/228630c) |
38
+ | [WhisperKit/openai_whisper-base](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-base) | [4.97](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-base/librispeech) | 67.2 | 145 | [Link](https://github.com/argmaxinc/WhisperKit/commit/228630c) |
39
+ | [WhisperKit/openai_whisper-tiny.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-tiny.en) | [5.61](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-tiny.en/librispeech) | 63.9 | 66 | [Link](https://github.com/argmaxinc/WhisperKit/commit/228630c) |
40
+ | [WhisperKit/openai_whisper-tiny](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-tiny) | [7.47](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-tiny/librispeech) | 52.5 | 66 | [Link](https://github.com/argmaxinc/WhisperKit/commit/228630c) |
41
 
42
  ## Dataset: `earnings22`
43
  Long-Form Audio (>1hr/clip) - 120 hours of earnings call recordings in English with various accents
44
 
45
+ | | WER (↓) | QoI (↑) | File Size (MB) | Code Commit |
46
+ |:------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------|----------:|-----------------:|:---------------------------------------------------------------|
47
+ | WhisperOpenAIAPI/openai_whisper-large-v2 | [16.27](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperOpenAIAPI/openai_whisper-large-v2/earnings22) | 100 | 3100 | N/A |
48
+ | [WhisperKit/openai_whisper-large-v3](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-large-v3) | [15.17](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-large-v3/earnings22) | 58.5 | 3100 | [Link](https://github.com/argmaxinc/WhisperKit/commit/2846fd9) |
49
+ | [WhisperKit/openai_whisper-base.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-base.en) | [23.49](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-base.en/earnings22) | 6.5 | 145 | [Link](https://github.com/argmaxinc/WhisperKit/commit/dda6571) |
50
+ | [WhisperKit/openai_whisper-tiny.en](https://hf.co/argmaxinc/whisperkit-coreml/tree/main/openai_whisper-tiny.en) | [28.64](https://hf.co/datasets/argmaxinc/whisperkit-evals/tree/main/WhisperKit/openai_whisper-tiny.en/earnings22) | 5.7 | 66 | [Link](https://github.com/argmaxinc/WhisperKit/commit/dda6571) |
 
51
 
52
 
53
+ ### Explanation
54
+
55
  We believe that rigorously measuring the quality of inference is necessary for developers and
56
  enterprises to make informed decisions when opting to use optimized or compressed variants of
57
  any machine learning model in production. To contextualize `WhisperKit`, we take the following Whisper
 
96
  - [earnings22](https://huggingface.co/datasets/argmaxinc/earnings22): ~120 hours of English audio clips from earnings calls with various accents, tests long-form transcription quality
97
 
98
  ### Reproducing Results
99
+ Benchmark results on this page were automatically generated by [whisperkittools](https://github.com/argmaxinc/whisperkittools). We use our cluster of Apple Silicon Macs as self-hosted runners on
100
+ Github Actions as our CI infrastructure to periodically recompute these benchmarks. Due to [security concerns](https://docs.github.com/en/actions/security-guides/security-hardening-for-github-actions#hardening-for-self-hosted-runners),
101
  we are unable to open up the cluster to the public. However, any Apple Silicon Mac (even with 8GB RAM) can be used to
102
  run identical [evaluation jobs](#evaluation) locally. For reference, our M2 Ultra devices complete a `librispeech` + `openai/whisper-large-v3`
103
+ evaluation in under 1 hour regardless of the Whisper implementation. Oldest Apple Silicon Macs should take less than 1 day to complete the same evaluation.
104
 
105
 
106