zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-21 15:11:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

Go: implement TTS for fishaudio, openrouter and asr for fishaudio (#14926)

Browse Source 
### What problem does this PR solve?

This PR implement TTS for FishAudio and MiniMax provider and ASR for
FishAudio

**The following functionalities are now supported:**

**FishAudio:**
- [x] Text To Speech
- [x] Stream Text To Speech
- [x] Audio To Text

**OpenRouter:**

- [x] Text To Speech

**Verified examples from the CLI:**
```plaintext

**FishAudio**

RAGFlow(user)> tts with 's1@test@fishaudio' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"reference_id": "90e65eaaf50e4470b8e6d43ee6afd7d5", "temperature": 0.7, "top_p": 0.7, "prosody": {"speed": 1, "volume": 0, "normalize_loudness": true}, "chunk_length": 300, "normalize": true, "sample_rate": 44100, "mp3_bitrate": 128, "latency": "normal", "max_new_tokens": 1024, "repetition_penalty": 1.2, "min_chunk_length": 50, "condition_on_previous_chunks": true, "early_stop_threshold": 1}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/s1_output.wav
SUCCESS

RAGFlow(user)> stream tts with 's1@test@fishaudio' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"reference_id": "90e65eaaf50e4470b8e6d43ee6afd7d5", "temperature": 0.7, "top_p": 0.7, "prosody": {"speed": 1, "volume": 0, "normalize_loudness": true}, "chunk_length": 300, "normalize": true, "sample_rate": 44100, "mp3_bitrate": 128, "latency": "normal", "max_new_tokens": 1024, "repetition_penalty": 1.2, "min_chunk_length": 50, "condition_on_previous_chunks": true, "early_stop_threshold": 1}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/s1_output.wav
SUCCESS

RAGFlow(user)> asr with 'transcribe-1@test@fishaudio' audio './internal/test.wav' param '{"language": "en", "ignore_timestamps": true}'
+----------------------------------------------------------------------------------------------------------------------+
| text                                                                                                                 |
+----------------------------------------------------------------------------------------------------------------------+
| The examination and testimony of the experts enabled the commission to conclude that five shots may have been fired. |
+----------------------------------------------------------------------------------------------------------------------+

```

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
This commit is contained in:
Haruko386
2026-05-14 18:58:00 +08:00
committed by GitHub
parent a98994ff91
commit 106f4b777e
9 changed files with 436 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
internal/cli/user_parser.go
View File

@@ -2753,7 +2753,7 @@ func (p *Parser) parseASRCommand() (*Command, error) {
if p.curToken.Type != TokenAudio {
return nil, fmt.Errorf("expected AUDIO to ASR")
}
p.nextToken() // consume FILE
p.nextToken() // consume AUDIO
audioFile, err := p.parseQuotedString()
if err != nil {
@@ -2761,14 +2761,29 @@ func (p *Parser) parseASRCommand() (*Command, error) {
}
p.nextToken()
cmd := NewCommand("asr_user_command")
cmd.Params["composite_model_name"] = compositeModelName
cmd.Params["audio_file"] = audioFile
for p.curToken.Type != TokenEOF && p.curToken.Type != TokenSemicolon {
switch p.curToken.Type {
case TokenParam:
p.nextToken()
if p.curToken.Type != TokenQuotedString {
return nil, fmt.Errorf("expect quoted string after 'param'")
}
cmd.Params["param_str"] = strings.Trim(p.curToken.Value, "\"'")
p.nextToken()
default:
return nil, fmt.Errorf("unexpected token in asr command: %s", p.curToken.Value)
}
}
// Semicolon is optional for UNSET TOKEN
if p.curToken.Type == TokenSemicolon {
p.nextToken()
}
cmd := NewCommand("asr_user_command")
cmd.Params["composite_model_name"] = compositeModelName
cmd.Params["audio_file"] = audioFile
return cmd, nil
}