Andrew Ng's "Reflective Three-Step Translation Method" is highly effective, improving translation quality by having the model self-review its results and suggest improvements. However, applying this method directly to SRT subtitle translation presents challenges.

Special Requirements of SRT Subtitle Format

SRT subtitle format has strict formatting requirements:

• First line: Line number
• Second line: Two timestamps, connected by -->, in the format hours:minutes:seconds,milliseconds
• Third line and after: Subtitle text content

Subtitles are separated by two blank lines.

Example:

1
00:00:01,950 --> 00:00:04,430
Several molecules have been discovered in the five-star system,

2
00:00:04,720 --> 00:00:06,780
We are still multiple universes away from third-type contact.

3
00:00:07,260 --> 00:00:09,880
Weibo has been carrying out filming missions for years now,

4
00:00:10,140 --> 00:00:12,920
Many previously difficult-to-capture photos have been transmitted recently.

Common Issues in SRT Translation

When using AI to translate SRT subtitles, the following problems may occur:

• Formatting Errors:
  • Missing line numbers or duplicate timestamps
  • Translating English symbols in timestamps into Chinese symbols
  • Merging adjacent subtitle texts into one line, especially when the preceding and following sentences form a complete sentence grammatically
• Translation Quality Issues:
  • Translation errors often occur, even with strict prompt constraints.

Examples of Common Errors:

• Subtitle text merging leading to blank lines

• Formatting chaos

• Line numbers being translated

• Inconsistent number of original and resulting subtitles

As mentioned above, when the preceding and following subtitles belong to the same sentence grammatically, they are likely to be translated into the same line, resulting in a missing subtitle.

Formatting errors directly prevent subsequent SRT-dependent processes from working. Different models have different errors and error probabilities. Relatively speaking, more intelligent models are more likely to return legal and compliant content, while small-scale locally deployed models are almost completely unusable.

However, given the improvement in translation quality from the three-step reflection method, I still tried it. Finally, I chose to use gemini-1.5-flash for a small test, mainly because it is intelligent enough and free. Aside from the frequency limit, there are almost no other restrictions.

Prompt Engineering Approach

Write prompts according to Andrew Ng's three-step reflection workflow:

• Step 1: Require the AI to translate literally.
• Step 2: Require the AI to evaluate the literal translation and provide optimization suggestions.
• Step 3: Re-translate based on the optimization suggestions.

The difference is to strengthen the requirement that the returned content must be in a legal SRT format, although it may not always comply.

Building a Simple API

One problem with the three-step reflection mode is the extra consumption of many more tokens. The prompts become longer, the output results become longer, and due to Gemini's frequency limit, exceeding the limit will return a 429 error. You need to pause for a while after each request.

Use Flask to build a backend API, and use Bootstrap 5 to create a simple single page for the front end. The overall interface is as follows:

Obviously, you must have a proxy to use Gemini domestically.

• Simultaneous translation lines: refers to the number of subtitle lines in one translation request. If it is too large, it may exceed the token limit and cause errors. If it is too small, it is meaningless. It is recommended to be within 30-100, with a default of 50.
• Pause seconds after translation: to prevent requests from being too frequent and causing a 429 error, it will pause for 10 seconds after each request before initiating the next request.

Example return result:

<step1_initial_translation>
1
00:00:01,950 --> 00:00:04,430
Several molecules have been discovered in the five-star system,

2
00:00:04,720 --> 00:00:06,780
We are still multiple universes away from third-type contact.

3
00:00:07,260 --> 00:00:09,880
Weibo has been carrying out filming missions for years now,

4
00:00:10,140 --> 00:00:12,920
Many previously difficult-to-capture photos have been transmitted recently.

5
00:00:13,440 --> 00:00:17,500
In early June, astronomers published this photo in Nature,

6
00:00:18,040 --> 00:00:19,180
Outside the blue core,

7
00:00:19,360 --> 00:00:21,380
There\'s also this circle of orange light,

8
00:00:21,900 --> 00:00:23,740
This is a new drama-scale sweet donut,

9
00:00:24,380 --> 00:00:25,640
This is a portal.

10
00:00:26,280 --> 00:00:28,100
This is the generation ring of an alien civilization,

</step1_initial_translation>

<step2_reflection>
* **Line 1:** "Five-star system" is likely a mistranslation.  It probably refers to a five-member committee or group, not a star system. Clarify the context.
* **Line 2:** "Multiple universes" seems like an over-exaggeration.  Rephrase for clarity and accuracy.
* **Line 3:** "Weibo" should be explained as a Chinese social media platform.  "Filming missions" is unclear.  Does it mean "posting videos/images"?
* **Line 8:** "Drama-scale sweet donut" is a nonsensical literal translation. Figure out the intended meaning.
* **Line 9:** "Portal" seems out of context.  Verify the intended meaning.
* **Line 10:** "Generation ring" is likely a mistranslation.  Clarify the context.
* **Line 11:** "Organic polycyclic aromatic hydrocarbons" is overly technical for a general audience. Simplify if possible.
* **Line 12 and 14:** Use the correct formatting for the galaxy\'s name: SPT0418-47.
* **Line 15:** "It hasn\'t been shortened" is awkward. Remove or rephrase.
* **Line 28:**  The name of the organization and the resource should be translated more naturally and accurately.  Consider breaking this long line into two for better readability.
* **Line 29:**  "Cute plush dolls" may sound childish. Consider rephrasing as "animated characters" or similar.
* **Line 35:** "James Webb Space Telescope" should be used consistently throughout. Shortening to "Webb Telescope" after the first mention is acceptable.
* **Line 44:** "SPD048" is likely a typo.  It should be SPT0418-47 to be consistent.
* **Line 45-46:**  "Standard beautiful photo" is redundant.  Simplify to "beautiful photo".
* **Line 48:** "Grovitational Lenshin" is a typo. Correct to "Gravitational Lensing".
* **Line 50:** The sentence is incomplete. Finish the thought.

</step2_reflection>

<step3_refined_translation>
1
00:00:01,950 --> 00:00:04,430
Several molecules have been discovered in the five-member group\'s area of focus.

2
00:00:04,720 --> 00:00:06,780
We are still far from making contact with extraterrestrial life.

3
00:00:07,260 --> 00:00:09,880
The James Webb Space Telescope has been capturing images for a year now,

4
00:00:10,140 --> 00:00:12,920
and has recently transmitted many previously unseen photos.

5
00:00:13,440 --> 00:00:17,500
In early June, astronomers published this image in Nature.

6
00:00:18,040 --> 00:00:19,180
Outside the blue core,

7
00:00:19,360 --> 00:00:21,380
there\'s a ring of orange light.

8
00:00:21,900 --> 00:00:23,740
This is a large, ring-shaped structure.

9
00:00:24,380 --> 00:00:25,640
This is being investigated.

10
00:00:26,280 --> 00:00:28,100
This is thought to be a sign of an early galaxy.

</step3_refined_translation>

Extract the text within the <step3_refined_translation></step3_refined_translation> tags from the result, which is the translation result.

Simple Package for Local Testing

Directly download, unzip, and double-click app.exe to automatically open the above UI interface in your browser. Enter the Key applied for in Gemini, fill in the proxy address, select the SRT subtitle file to be translated, and select the target language to be translated to, and test the results.

Q1: How does the reflection workflow differ from traditional machine translation?

A1: The reflection workflow introduces a self-assessment and optimization mechanism, simulating the thinking process of a human translator, and can produce more accurate and natural translation results.

Q2: How long does it take to use the reflection workflow?

A2: Although the reflection workflow requires multiple AI processing steps, it usually only takes 10–20 seconds longer than traditional methods. Considering the improvement in translation quality, this time investment is worthwhile.

Q3: Can the reflection workflow guarantee that the subtitle translation result is a legal SRT?

A3: No, there may still be problems with blank lines and inconsistencies with the number of original subtitles. For example, if there are only 3-5 words in the latter of two consecutive subtitles, and grammatically it is a continuation of the previous sentence, the translation result is likely to be merged into one.

---

---

Added a function to the small tool to support uploading video or audio files at the same time. With the help of Gemini, the audio and video can be converted into subtitles, and the translation can be performed while converting into subtitles, and the translation results can be returned.

The Gemini large model itself supports both text and audio-visual formats, so a request can realize the transcription of audio and video into subtitles and translation.

For example, if an English-speaking video is sent to Gemini and specified to be translated into Chinese, the returned result will be Chinese subtitles.

1. Translate Subtitles Only

You can paste SRT format subtitle content into the left text box, or directly click the "Upload SRT Subtitles" button to select a subtitle file from your local computer.

Then set the target language you want to translate to, and you can use the "Three-Step Reflection Translation Method" to direct Gemini to perform the translation task, return the results to the text box on the right, and click the "Download Button" in the lower right corner to save it as an SRT file to your local computer.

2. Transcribe Audio and Video into Subtitles

Click the "Upload Audio and Video to Transcribe into Subtitles" button on the left, select any audio or video file to upload. After uploading, submit it. After processing, Gemini will return the subtitle content recognized based on the speaking voice in the audio and video, and the effect is good.

If you specify the target language at the same time, Gemini will continue to translate the result into the language you specify after recognition, and then return it. That is, it completes two tasks of generating subtitles and translating subtitles at the same time.

Download Address:

https://github.com/jianchang512/ai2srt/releases/download/v0.2/windows-ai2srt-0.2.7z