Masao-Taketani commited on
Commit
dcb3fad
·
verified ·
1 Parent(s): 75023a5

add finetuning instructions

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -378,6 +378,16 @@ sf.write("tts_jp.wav", waveform.cpu()[0], 24_000)
378
  </tr>
379
  </table>
380
 
 
 
 
 
 
 
 
 
 
 
381
  ## 📬 Contact
382
 
383
  - Got questions or want to connect? [Join our Discord community](https://discord.com/invite/liquid-ai)
 
378
  </tr>
379
  </table>
380
 
381
+ ## Finetuning
382
+
383
+ To finetune on your own data, make use of the `ChatMessage` interface. This requires you to:
384
+
385
+ 1. map your raw dataset rows into `list[ChatMessage]`
386
+ 2. use the [`LFM2AudioChatMapper`](src/liquid_audio/data/mapper.py) to create a preprocessed dataset
387
+ 3. train a model from the preprocessed dataset with `LFM2DataLoader`
388
+
389
+ To finetune our Japanese model on your own data in interleaved generation mode, instantiate the `LFM2AudioChatMapper` class with `interleaved_text_tokens=6` and `interleaved_audio_tokens=9`. These values reflect the predefined Japanese interleaving ratio of 6 text tokens to 9 audio tokens, based on tokenization statistics.
390
+
391
  ## 📬 Contact
392
 
393
  - Got questions or want to connect? [Join our Discord community](https://discord.com/invite/liquid-ai)