|
|
|
|
|
import sys |
|
import os |
|
|
|
sys.path.append(os.getcwd()) |
|
|
|
import multiprocessing as mp |
|
import numpy as np |
|
|
|
from model.utils import ( |
|
get_seed_tts_test, |
|
run_asr_wer, |
|
run_sim, |
|
) |
|
|
|
|
|
eval_task = "wer" |
|
lang = "zh" |
|
metalst = f"data/seedtts_testset/{lang}/meta.lst" |
|
|
|
gen_wav_dir = "PATH_TO_GENERATED" |
|
|
|
|
|
|
|
|
|
gpus = [0, 1, 2, 3, 4, 5, 6, 7] |
|
test_set = get_seed_tts_test(metalst, gen_wav_dir, gpus) |
|
|
|
local = False |
|
if local: |
|
if lang == "zh": |
|
asr_ckpt_dir = "../checkpoints/funasr" |
|
elif lang == "en": |
|
asr_ckpt_dir = "../checkpoints/Systran/faster-whisper-large-v3" |
|
else: |
|
asr_ckpt_dir = "" |
|
|
|
wavlm_ckpt_dir = "../checkpoints/UniSpeech/wavlm_large_finetune.pth" |
|
|
|
|
|
|
|
|
|
if eval_task == "wer": |
|
wers = [] |
|
|
|
with mp.Pool(processes=len(gpus)) as pool: |
|
args = [(rank, lang, sub_test_set, asr_ckpt_dir) for (rank, sub_test_set) in test_set] |
|
results = pool.map(run_asr_wer, args) |
|
for wers_ in results: |
|
wers.extend(wers_) |
|
|
|
wer = round(np.mean(wers) * 100, 3) |
|
print(f"\nTotal {len(wers)} samples") |
|
print(f"WER : {wer}%") |
|
|
|
|
|
|
|
|
|
if eval_task == "sim": |
|
sim_list = [] |
|
|
|
with mp.Pool(processes=len(gpus)) as pool: |
|
args = [(rank, sub_test_set, wavlm_ckpt_dir) for (rank, sub_test_set) in test_set] |
|
results = pool.map(run_sim, args) |
|
for sim_ in results: |
|
sim_list.extend(sim_) |
|
|
|
sim = round(sum(sim_list) / len(sim_list), 3) |
|
print(f"\nTotal {len(sim_list)} samples") |
|
print(f"SIM : {sim}") |
|
|