|
@@ -93,7 +93,7 @@ export OUTPUT_DIR="tmp/" # Output directory for generated text/unit/waveform
|
|
export TGT_TEXT_COL="tgt_text" # The column in your ${TEST_SET_TSV} for reference target text to calcuate BLEU score. You can skip this argument.
|
|
export TGT_TEXT_COL="tgt_text" # The column in your ${TEST_SET_TSV} for reference target text to calcuate BLEU score. You can skip this argument.
|
|
export DFACTOR="1.0" # Duration factor for model inference to tune predicted duration (preddur=DFACTOR*preddur) per each position which affects output speech rate. Greater value means slower speech rate (default to 1.0). See expressive evaluation README for details on duration factor we used.
|
|
export DFACTOR="1.0" # Duration factor for model inference to tune predicted duration (preddur=DFACTOR*preddur) per each position which affects output speech rate. Greater value means slower speech rate (default to 1.0). See expressive evaluation README for details on duration factor we used.
|
|
python src/seamless_communication/cli/expressivity/evaluate/pretssel_inference.py \
|
|
python src/seamless_communication/cli/expressivity/evaluate/pretssel_inference.py \
|
|
- ${TEST_SET_TSV} --model-dir ${MODEL_DIR} --task s2st --tgt_lang ${TGT_LANG}\
|
|
|
|
|
|
+ ${TEST_SET_TSV} --gated-model-dir ${MODEL_DIR} --task s2st --tgt_lang ${TGT_LANG}\
|
|
--audio_root_dir "" --output_path ${OUTPUT_DIR} --ref_field ${TGT_TEXT_COL} \
|
|
--audio_root_dir "" --output_path ${OUTPUT_DIR} --ref_field ${TGT_TEXT_COL} \
|
|
--model_name seamless_expressivity --vocoder_name vocoder_pretssel \
|
|
--model_name seamless_expressivity --vocoder_name vocoder_pretssel \
|
|
--unit_generation_beam_size 1 --duration_factor ${DFACTOR}
|
|
--unit_generation_beam_size 1 --duration_factor ${DFACTOR}
|