Skip to content

docs: update speech-to-text benchmarks #1014

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
IgorSwat merged 1 commit into from
Mar 25, 2026
+4 −4
Merged

docs: update speech-to-text benchmarks #1014

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/docs/02-benchmarks/inference-time.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,15 +139,15 @@ Average time for encoding audio of given length over 10 runs. For `Whisper` mode

| Model | iPhone 17 Pro (XNNPACK) [ms] | iPhone 16 Pro (XNNPACK) [ms] | iPhone SE 3 (XNNPACK) [ms] | Samsung Galaxy S24 (XNNPACK) [ms] | OnePlus 12 (XNNPACK) [ms] |
| ------------------ | :--------------------------: | :--------------------------: | :------------------------: | :-------------------------------: | :-----------------------: |
| Whisper-tiny (30s) | 248 | 254 | 1145 | 435 | 526 |
| Whisper-tiny (30s) | 89 | 93 | 403 | 277 | 260 |

### Decoding

Average time for decoding one token in sequence of approximately 100 tokens, with encoding context is obtained from audio of noted length.

| Model | iPhone 17 Pro (XNNPACK) [ms] | iPhone 16 Pro (XNNPACK) [ms] | iPhone SE 3 (XNNPACK) [ms] | Samsung Galaxy S24 (XNNPACK) [ms] | OnePlus 12 (XNNPACK) [ms] |
| ------------------ | :--------------------------: | :--------------------------: | :------------------------: | :-------------------------------: | :-----------------------: |
| Whisper-tiny (30s) | 23 | 25 | 121 | 92 | 115 |
| Whisper-tiny (30s) | 6 | 6 | 40 | 28 | 25 |

## Text to Speech

Expand Down
4 changes: 2 additions & 2 deletions docs/versioned_docs/version-0.8.x/02-benchmarks/inference-time.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,15 +139,15 @@ Average time for encoding audio of given length over 10 runs. For `Whisper` mode

| Model | iPhone 17 Pro (XNNPACK) [ms] | iPhone 16 Pro (XNNPACK) [ms] | iPhone SE 3 (XNNPACK) [ms] | Samsung Galaxy S24 (XNNPACK) [ms] | OnePlus 12 (XNNPACK) [ms] |
| ------------------ | :--------------------------: | :--------------------------: | :------------------------: | :-------------------------------: | :-----------------------: |
| Whisper-tiny (30s) | 248 | 254 | 1145 | 435 | 526 |
| Whisper-tiny (30s) | 89 | 93 | 403 | 277 | 260 |

### Decoding

Average time for decoding one token in sequence of approximately 100 tokens, with encoding context is obtained from audio of noted length.

| Model | iPhone 17 Pro (XNNPACK) [ms] | iPhone 16 Pro (XNNPACK) [ms] | iPhone SE 3 (XNNPACK) [ms] | Samsung Galaxy S24 (XNNPACK) [ms] | OnePlus 12 (XNNPACK) [ms] |
| ------------------ | :--------------------------: | :--------------------------: | :------------------------: | :-------------------------------: | :-----------------------: |
| Whisper-tiny (30s) | 23 | 25 | 121 | 92 | 115 |
| Whisper-tiny (30s) | 6 | 6 | 40 | 28 | 25 |

## Text to Speech

Expand Down
Loading