|
|
@@ -18,7 +18,7 @@ llm: !new:cosyvoice.llm.llm.TransformerLM
|
|
|
text_encoder_input_size: !ref <text_encoder_input_size>
|
|
|
llm_input_size: !ref <llm_input_size>
|
|
|
llm_output_size: !ref <llm_output_size>
|
|
|
- text_token_size: 51866
|
|
|
+ text_token_size: 51866 # change to 60515 if you want to train with CosyVoice-300M-25Hz recipe
|
|
|
speech_token_size: 4096
|
|
|
length_normalized_loss: True
|
|
|
lsm_weight: 0
|
|
|
@@ -54,6 +54,11 @@ llm: !new:cosyvoice.llm.llm.TransformerLM
|
|
|
pos_enc_layer_type: 'rel_pos_espnet'
|
|
|
selfattention_layer_type: 'rel_selfattn'
|
|
|
static_chunk_size: 1
|
|
|
+ sampling: !name:cosyvoice.utils.common.ras_sampling
|
|
|
+ top_p: 0.8
|
|
|
+ top_k: 25
|
|
|
+ win_size: 10
|
|
|
+ tau_r: 0.1
|
|
|
|
|
|
flow: !new:cosyvoice.flow.flow.MaskedDiffWithXvec
|
|
|
input_size: 512
|
|
|
@@ -61,7 +66,7 @@ flow: !new:cosyvoice.flow.flow.MaskedDiffWithXvec
|
|
|
spk_embed_dim: !ref <spk_embed_dim>
|
|
|
output_type: 'mel'
|
|
|
vocab_size: 4096
|
|
|
- input_frame_rate: 50
|
|
|
+ input_frame_rate: 50 # change to 25 if you want to train with CosyVoice-300M-25Hz recipe
|
|
|
only_mask_loss: True
|
|
|
encoder: !new:cosyvoice.transformer.encoder.ConformerEncoder
|
|
|
output_size: 512
|
|
|
@@ -130,7 +135,7 @@ hift: !new:cosyvoice.hifigan.generator.HiFTGenerator
|
|
|
|
|
|
# processor functions
|
|
|
parquet_opener: !name:cosyvoice.dataset.processor.parquet_opener
|
|
|
-get_tokenizer: !name:whisper.tokenizer.get_tokenizer
|
|
|
+get_tokenizer: !name:whisper.tokenizer.get_tokenizer # change to !name:cosyvoice.tokenizer.tokenizer.get_tokenizer if you want to train with CosyVoice-300M-25Hz recipe
|
|
|
multilingual: True
|
|
|
num_languages: 100
|
|
|
language: 'en'
|
lyuxiang.lx