From: Thijs Raymakers <redacted>
Date: Sat, 29 Apr 2023 15:55:37 +0000 (+0200)
Subject: whisper : use correct seek_end when offset is used (#833)
X-Git-Tag: upstream/1.7.4~1471
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=6108d3cc580e6ca80ee265c6fcc306e29dc62645;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

whisper : use correct seek_end when offset is used (#833)

Whenever an `offset_ms` is provided, the value of `seek_end` is
calculated incorrectly. This causes Whisper to keep transcribing
after the end of the file.

The current behavior looks like
```
[00:34:40.000 --> 00:34:47.000]   This is an example audio file.
[00:34:47.000 --> 00:34:49.000]   The text has been redacted
[00:34:49.000 --> 00:34:51.000]   This is the end of the audio.
[00:34:51.000 --> 00:34:52.000]   ***
[00:34:52.000 --> 00:34:53.000]   ***
[00:34:53.000 --> 00:34:54.000]   ***
[00:34:55.000 --> 00:34:56.000]   ***
...
```

The expected behavior should be
```
[00:34:40.000 --> 00:34:47.000]   This is an example audio file.
[00:34:47.000 --> 00:34:49.000]   The text has been redacted
[00:34:49.000 --> 00:34:51.000]   This is the end of the audio.
- end of program -
```

This commit changes the calculation of the `seek_end` variable to
only add `seek_start` if a custom `duration_ms` is provided.
Otherwise, it defaults to the end of the file.

Signed-off-by: Thijs Raymakers <redacted>
---

diff --git a/whisper.cpp b/whisper.cpp
index 44341410..2c489b92 100644
--- a/whisper.cpp
+++ b/whisper.cpp
@@ -3855,7 +3855,7 @@ int whisper_full_with_state(
     }
 
     const int seek_start = params.offset_ms/10;
-    const int seek_end = seek_start + (params.duration_ms == 0 ? whisper_n_len_from_state(state) : params.duration_ms/10);
+    const int seek_end = params.duration_ms == 0 ? whisper_n_len_from_state(state) : seek_start + params.duration_ms/10;
 
     // if length of spectrogram is less than 1s (100 samples), then return
     // basically don't process anything that is less than 1s