feat(model/cosyvoice): support hot_fix params and max_prompt_audio_length

[songguocola]

…ngth

[gemini-code-assist]

Summary of Changes

Hello @songguocola, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request expands the functionality of the 'cosyvoice' model by introducing advanced speech synthesis customization through "hotfix" parameters, enabling users to define specific pronunciation and text replacement rules. Additionally, it provides more granular control over voice enrollment by allowing the specification of a maximum prompt audio length. These changes aim to improve the flexibility and precision of audio generation and voice model training.

Highlights

• Speech Synthesis Hotfix Parameters: Introduced support for 'hot_fix' parameters in speech synthesis, allowing users to define custom pronunciation and text replacement rules for enhanced audio output.
• Voice Enrollment Prompt Audio Length Control: Added a 'max_prompt_audio_length' parameter to voice enrollment, providing more granular control over the maximum duration of prompt audio used.
• Dynamic Voice Parameter Handling: Enhanced 'MultiModalConversationParam' to flexibly retrieve the 'VOICE' parameter from a generic 'parameters' map, improving dynamic voice selection.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• src/main/java/com/alibaba/dashscope/aigc/multimodalconversation/MultiModalConversationParam.java
  • Added a conditional check to set the 'VOICE' property from the 'parameters' map if available, providing more dynamic voice selection.
• src/main/java/com/alibaba/dashscope/audio/tts/SpeechSynthesisApiKeywords.java
  • Introduced new API keywords: 'HOT_FIX', 'PRONUNCIATION', and 'REPLACE' to support the new hotfix functionality.
• src/main/java/com/alibaba/dashscope/audio/ttsv2/ParamHotFix.java
  • Created a new class 'ParamHotFix' to encapsulate pronunciation and replacement rules for speech synthesis.
  • Includes nested 'PronunciationItem' and 'ReplaceItem' classes for structured data.
  • Provides methods to convert these rules into a format suitable for API requests.
• src/main/java/com/alibaba/dashscope/audio/ttsv2/SpeechSynthesisParam.java
  • Added a 'hotFix' field to the 'SpeechSynthesisParam' class.
  • Implemented logic within 'getParameters()' to serialize 'hotFix' rules into the request payload if present.
• src/main/java/com/alibaba/dashscope/audio/ttsv2/enrollment/VoiceEnrollmentParam.java
  • Added a 'maxPromptAudioLength' field with a default value of 10.0f.
  • Included logic to add 'max_prompt_audio_length' to the input JSON if its value is greater than 0.
• src/main/java/com/alibaba/dashscope/audio/ttsv2/enrollment/VoiceEnrollmentService.java
  • Modified the 'createVoice' method to pass the new 'maxPromptAudioLength' parameter when building 'VoiceEnrollmentParam'.
• src/test/java/com/alibaba/dashscope/TestTtsV2SpeechSynthesizer.java
  • Added test code to demonstrate the usage of 'ParamHotFix' with pronunciation and replacement rules in 'testStreamingCall()'.

Activity

• No specific activity (comments, reviews, or progress updates) has been recorded for this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request adds support for hot_fix parameters in cosyvoice and a max_prompt_audio_length parameter. The changes look good overall, but I have a few suggestions to improve code safety, readability, and adherence to best practices. My main concerns are a potential ClassCastException due to an unsafe cast, and opportunities to refactor some of the new code for better type safety and conciseness.