deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

update dataset

Browse Source
This commit is contained in:
lyuxiang.lx
2025-12-29 12:46:34 +00:00
parent 63a06227d1
commit 4c19646b9a
3 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
cosyvoice/dataset/dataset.py
View File

@@ -145,7 +145,11 @@ def Dataset(data_list_file,
shuffle=shuffle, shuffle=shuffle,
partition=partition) partition=partition)
# map partial arg to padding func # map partial arg to padding func
data_pipeline[-1] = partial(data_pipeline[-1], gan=gan, dpo=dpo) for i in range(1, len(data_pipeline)):
if data_pipeline[i].func.__name__ == 'compute_fbank':
data_pipeline[i] = partial(data_pipeline[i], token_mel_ratio=0)
if data_pipeline[i].func.__name__ == 'padding':
data_pipeline[i] = partial(data_pipeline[i], gan=gan, dpo=dpo)
for func in data_pipeline: for func in data_pipeline:
dataset = Processor(dataset, func, mode=mode) dataset = Processor(dataset, func, mode=mode)
return dataset return dataset

1
examples/libritts/cosyvoice2/run.sh
View File

@@ -66,7 +66,6 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
fi fi
cat data/{train-clean-100,train-clean-360,train-other-500}/parquet/data.list > data/train.data.list cat data/{train-clean-100,train-clean-360,train-other-500}/parquet/data.list > data/train.data.list
cat data/{dev-clean,dev-other}/parquet/data.list > data/dev.data.list cat data/{dev-clean,dev-other}/parquet/data.list > data/dev.data.list
# NOTE will update llm/hift training later
for model in llm flow hifigan; do for model in llm flow hifigan; do
torchrun --nnodes=1 --nproc_per_node=$num_gpus \ torchrun --nnodes=1 --nproc_per_node=$num_gpus \
--rdzv_id=$job_id --rdzv_backend="c10d" --rdzv_endpoint="localhost:1234" \ --rdzv_id=$job_id --rdzv_backend="c10d" --rdzv_endpoint="localhost:1234" \

1
examples/libritts/cosyvoice3/run.sh
View File

@@ -68,7 +68,6 @@ if [ ${stage} -le 5 ] && [ ${stop_stage} -ge 5 ]; then
fi fi
cat data/{train-clean-100,train-clean-360,train-other-500}/parquet/data.list > data/train.data.list cat data/{train-clean-100,train-clean-360,train-other-500}/parquet/data.list > data/train.data.list
cat data/{dev-clean,dev-other}/parquet/data.list > data/dev.data.list cat data/{dev-clean,dev-other}/parquet/data.list > data/dev.data.list
# NOTE will update llm/hift training later
for model in llm flow hifigan; do for model in llm flow hifigan; do
torchrun --nnodes=1 --nproc_per_node=$num_gpus \ torchrun --nnodes=1 --nproc_per_node=$num_gpus \
--rdzv_id=$job_id --rdzv_backend="c10d" --rdzv_endpoint="localhost:1234" \ --rdzv_id=$job_id --rdzv_backend="c10d" --rdzv_endpoint="localhost:1234" \