Files
spark-pocket-tts/pocket_tts/config/english.yaml
T
Gabriel de Marmiesse c90fc8ced6 Add french, italian, portuguese, spanish, german (#155)
The french 6 layers variant wasn't included because it's not good enough
yet. Use the `french_24l` variant for now.
2026-04-17 17:52:16 +02:00

62 lines
1.4 KiB
YAML

# sig: a0ac5076.yaml
weights_path: hf://kyutai/pocket-tts/languages/english/model.safetensors@39592ff23c9ef80098bb74895d104c26275fe2c9
weights_path_without_voice_cloning: hf://kyutai/pocket-tts-without-voice-cloning/languages/english/model.safetensors@d29db7978e464fb90cb3359ee0c69a273b9142cc
flow_lm:
insert_bos_before_voice: true
dtype: float32
flow:
depth: 6
dim: 512
transformer:
d_model: 1024
hidden_scale: 4
max_period: 10000
num_heads: 16
num_layers: 6
lookup_table:
dim: 1024
n_bins: 4000
tokenizer: sentencepiece
tokenizer_path: hf://kyutai/pocket-tts-without-voice-cloning/languages/english/tokenizer.model@d29db7978e464fb90cb3359ee0c69a273b9142cc
#weights_path: final.safetensors
mimi:
dtype: float32
sample_rate: 24000
inner_dim: 32
outer_dim: 512
channels: 1
frame_rate: 12.5
seanet:
dimension: 512
channels: 1
n_filters: 64
n_residual_layers: 1
ratios:
- 6
- 5
- 4
kernel_size: 7
residual_kernel_size: 3
last_kernel_size: 3
dilation_base: 2
pad_mode: constant
compress: 2
transformer:
d_model: 512
num_heads: 8
num_layers: 2
layer_scale: 0.01
context: 250
dim_feedforward: 2048
input_dimension: 512
output_dimensions:
- 512
quantizer:
dimension: 32
output_dimension: 512
#weights_path: codec.safetensors