xinference 1.0.1__py3-none-any.whl → 1.1.0__py3-none-any.whl

xinference/thirdparty/f5_tts/eval/ecapa_tdnn.py

@@ -0,0 +1,330 @@
+# just for speaker similarity evaluation, third-party code
+
+# From https://github.com/microsoft/UniSpeech/blob/main/downstreams/speaker_verification/models/
+# part of the code is borrowed from https://github.com/lawlict/ECAPA-TDNN
+
+import os
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+""" Res2Conv1d + BatchNorm1d + ReLU
+"""
+
+
+class Res2Conv1dReluBn(nn.Module):
+    """
+    in_channels == out_channels == channels
+    """
+
+    def __init__(self, channels, kernel_size=1, stride=1, padding=0, dilation=1, bias=True, scale=4):
+        super().__init__()
+        assert channels % scale == 0, "{} % {} != 0".format(channels, scale)
+        self.scale = scale
+        self.width = channels // scale
+        self.nums = scale if scale == 1 else scale - 1
+
+        self.convs = []
+        self.bns = []
+        for i in range(self.nums):
+            self.convs.append(nn.Conv1d(self.width, self.width, kernel_size, stride, padding, dilation, bias=bias))
+            self.bns.append(nn.BatchNorm1d(self.width))
+        self.convs = nn.ModuleList(self.convs)
+        self.bns = nn.ModuleList(self.bns)
+
+    def forward(self, x):
+        out = []
+        spx = torch.split(x, self.width, 1)
+        for i in range(self.nums):
+            if i == 0:
+                sp = spx[i]
+            else:
+                sp = sp + spx[i]
+            # Order: conv -> relu -> bn
+            sp = self.convs[i](sp)
+            sp = self.bns[i](F.relu(sp))
+            out.append(sp)
+        if self.scale != 1:
+            out.append(spx[self.nums])
+        out = torch.cat(out, dim=1)
+
+        return out
+
+
+""" Conv1d + BatchNorm1d + ReLU
+"""
+
+
+class Conv1dReluBn(nn.Module):
+    def __init__(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, dilation=1, bias=True):
+        super().__init__()
+        self.conv = nn.Conv1d(in_channels, out_channels, kernel_size, stride, padding, dilation, bias=bias)
+        self.bn = nn.BatchNorm1d(out_channels)
+
+    def forward(self, x):
+        return self.bn(F.relu(self.conv(x)))
+
+
+""" The SE connection of 1D case.
+"""
+
+
+class SE_Connect(nn.Module):
+    def __init__(self, channels, se_bottleneck_dim=128):
+        super().__init__()
+        self.linear1 = nn.Linear(channels, se_bottleneck_dim)
+        self.linear2 = nn.Linear(se_bottleneck_dim, channels)
+
+    def forward(self, x):
+        out = x.mean(dim=2)
+        out = F.relu(self.linear1(out))
+        out = torch.sigmoid(self.linear2(out))
+        out = x * out.unsqueeze(2)
+
+        return out
+
+
+""" SE-Res2Block of the ECAPA-TDNN architecture.
+"""
+
+# def SE_Res2Block(channels, kernel_size, stride, padding, dilation, scale):
+#     return nn.Sequential(
+#         Conv1dReluBn(channels, 512, kernel_size=1, stride=1, padding=0),
+#         Res2Conv1dReluBn(512, kernel_size, stride, padding, dilation, scale=scale),
+#         Conv1dReluBn(512, channels, kernel_size=1, stride=1, padding=0),
+#         SE_Connect(channels)
+#     )
+
+
+class SE_Res2Block(nn.Module):
+    def __init__(self, in_channels, out_channels, kernel_size, stride, padding, dilation, scale, se_bottleneck_dim):
+        super().__init__()
+        self.Conv1dReluBn1 = Conv1dReluBn(in_channels, out_channels, kernel_size=1, stride=1, padding=0)
+        self.Res2Conv1dReluBn = Res2Conv1dReluBn(out_channels, kernel_size, stride, padding, dilation, scale=scale)
+        self.Conv1dReluBn2 = Conv1dReluBn(out_channels, out_channels, kernel_size=1, stride=1, padding=0)
+        self.SE_Connect = SE_Connect(out_channels, se_bottleneck_dim)
+
+        self.shortcut = None
+        if in_channels != out_channels:
+            self.shortcut = nn.Conv1d(
+                in_channels=in_channels,
+                out_channels=out_channels,
+                kernel_size=1,
+            )
+
+    def forward(self, x):
+        residual = x
+        if self.shortcut:
+            residual = self.shortcut(x)
+
+        x = self.Conv1dReluBn1(x)
+        x = self.Res2Conv1dReluBn(x)
+        x = self.Conv1dReluBn2(x)
+        x = self.SE_Connect(x)
+
+        return x + residual
+
+
+""" Attentive weighted mean and standard deviation pooling.
+"""
+
+
+class AttentiveStatsPool(nn.Module):
+    def __init__(self, in_dim, attention_channels=128, global_context_att=False):
+        super().__init__()
+        self.global_context_att = global_context_att
+
+        # Use Conv1d with stride == 1 rather than Linear, then we don't need to transpose inputs.
+        if global_context_att:
+            self.linear1 = nn.Conv1d(in_dim * 3, attention_channels, kernel_size=1)  # equals W and b in the paper
+        else:
+            self.linear1 = nn.Conv1d(in_dim, attention_channels, kernel_size=1)  # equals W and b in the paper
+        self.linear2 = nn.Conv1d(attention_channels, in_dim, kernel_size=1)  # equals V and k in the paper
+
+    def forward(self, x):
+        if self.global_context_att:
+            context_mean = torch.mean(x, dim=-1, keepdim=True).expand_as(x)
+            context_std = torch.sqrt(torch.var(x, dim=-1, keepdim=True) + 1e-10).expand_as(x)
+            x_in = torch.cat((x, context_mean, context_std), dim=1)
+        else:
+            x_in = x
+
+        # DON'T use ReLU here! In experiments, I find ReLU hard to converge.
+        alpha = torch.tanh(self.linear1(x_in))
+        # alpha = F.relu(self.linear1(x_in))
+        alpha = torch.softmax(self.linear2(alpha), dim=2)
+        mean = torch.sum(alpha * x, dim=2)
+        residuals = torch.sum(alpha * (x**2), dim=2) - mean**2
+        std = torch.sqrt(residuals.clamp(min=1e-9))
+        return torch.cat([mean, std], dim=1)
+
+
+class ECAPA_TDNN(nn.Module):
+    def __init__(
+        self,
+        feat_dim=80,
+        channels=512,
+        emb_dim=192,
+        global_context_att=False,
+        feat_type="wavlm_large",
+        sr=16000,
+        feature_selection="hidden_states",
+        update_extract=False,
+        config_path=None,
+    ):
+        super().__init__()
+
+        self.feat_type = feat_type
+        self.feature_selection = feature_selection
+        self.update_extract = update_extract
+        self.sr = sr
+
+        torch.hub._validate_not_a_forked_repo = lambda a, b, c: True
+        try:
+            local_s3prl_path = os.path.expanduser("~/.cache/torch/hub/s3prl_s3prl_main")
+            self.feature_extract = torch.hub.load(local_s3prl_path, feat_type, source="local", config_path=config_path)
+        except:  # noqa: E722
+            self.feature_extract = torch.hub.load("s3prl/s3prl", feat_type)
+
+        if len(self.feature_extract.model.encoder.layers) == 24 and hasattr(
+            self.feature_extract.model.encoder.layers[23].self_attn, "fp32_attention"
+        ):
+            self.feature_extract.model.encoder.layers[23].self_attn.fp32_attention = False
+        if len(self.feature_extract.model.encoder.layers) == 24 and hasattr(
+            self.feature_extract.model.encoder.layers[11].self_attn, "fp32_attention"
+        ):
+            self.feature_extract.model.encoder.layers[11].self_attn.fp32_attention = False
+
+        self.feat_num = self.get_feat_num()
+        self.feature_weight = nn.Parameter(torch.zeros(self.feat_num))
+
+        if feat_type != "fbank" and feat_type != "mfcc":
+            freeze_list = ["final_proj", "label_embs_concat", "mask_emb", "project_q", "quantizer"]
+            for name, param in self.feature_extract.named_parameters():
+                for freeze_val in freeze_list:
+                    if freeze_val in name:
+                        param.requires_grad = False
+                        break
+
+        if not self.update_extract:
+            for param in self.feature_extract.parameters():
+                param.requires_grad = False
+
+        self.instance_norm = nn.InstanceNorm1d(feat_dim)
+        # self.channels = [channels] * 4 + [channels * 3]
+        self.channels = [channels] * 4 + [1536]
+
+        self.layer1 = Conv1dReluBn(feat_dim, self.channels[0], kernel_size=5, padding=2)
+        self.layer2 = SE_Res2Block(
+            self.channels[0],
+            self.channels[1],
+            kernel_size=3,
+            stride=1,
+            padding=2,
+            dilation=2,
+            scale=8,
+            se_bottleneck_dim=128,
+        )
+        self.layer3 = SE_Res2Block(
+            self.channels[1],
+            self.channels[2],
+            kernel_size=3,
+            stride=1,
+            padding=3,
+            dilation=3,
+            scale=8,
+            se_bottleneck_dim=128,
+        )
+        self.layer4 = SE_Res2Block(
+            self.channels[2],
+            self.channels[3],
+            kernel_size=3,
+            stride=1,
+            padding=4,
+            dilation=4,
+            scale=8,
+            se_bottleneck_dim=128,
+        )
+
+        # self.conv = nn.Conv1d(self.channels[-1], self.channels[-1], kernel_size=1)
+        cat_channels = channels * 3
+        self.conv = nn.Conv1d(cat_channels, self.channels[-1], kernel_size=1)
+        self.pooling = AttentiveStatsPool(
+            self.channels[-1], attention_channels=128, global_context_att=global_context_att
+        )
+        self.bn = nn.BatchNorm1d(self.channels[-1] * 2)
+        self.linear = nn.Linear(self.channels[-1] * 2, emb_dim)
+
+    def get_feat_num(self):
+        self.feature_extract.eval()
+        wav = [torch.randn(self.sr).to(next(self.feature_extract.parameters()).device)]
+        with torch.no_grad():
+            features = self.feature_extract(wav)
+        select_feature = features[self.feature_selection]
+        if isinstance(select_feature, (list, tuple)):
+            return len(select_feature)
+        else:
+            return 1
+
+    def get_feat(self, x):
+        if self.update_extract:
+            x = self.feature_extract([sample for sample in x])
+        else:
+            with torch.no_grad():
+                if self.feat_type == "fbank" or self.feat_type == "mfcc":
+                    x = self.feature_extract(x) + 1e-6  # B x feat_dim x time_len
+                else:
+                    x = self.feature_extract([sample for sample in x])
+
+        if self.feat_type == "fbank":
+            x = x.log()
+
+        if self.feat_type != "fbank" and self.feat_type != "mfcc":
+            x = x[self.feature_selection]
+            if isinstance(x, (list, tuple)):
+                x = torch.stack(x, dim=0)
+            else:
+                x = x.unsqueeze(0)
+            norm_weights = F.softmax(self.feature_weight, dim=-1).unsqueeze(-1).unsqueeze(-1).unsqueeze(-1)
+            x = (norm_weights * x).sum(dim=0)
+            x = torch.transpose(x, 1, 2) + 1e-6
+
+        x = self.instance_norm(x)
+        return x
+
+    def forward(self, x):
+        x = self.get_feat(x)
+
+        out1 = self.layer1(x)
+        out2 = self.layer2(out1)
+        out3 = self.layer3(out2)
+        out4 = self.layer4(out3)
+
+        out = torch.cat([out2, out3, out4], dim=1)
+        out = F.relu(self.conv(out))
+        out = self.bn(self.pooling(out))
+        out = self.linear(out)
+
+        return out
+
+
+def ECAPA_TDNN_SMALL(
+    feat_dim,
+    emb_dim=256,
+    feat_type="wavlm_large",
+    sr=16000,
+    feature_selection="hidden_states",
+    update_extract=False,
+    config_path=None,
+):
+    return ECAPA_TDNN(
+        feat_dim=feat_dim,
+        channels=512,
+        emb_dim=emb_dim,
+        feat_type=feat_type,
+        sr=sr,
+        feature_selection=feature_selection,
+        update_extract=update_extract,
+        config_path=config_path,
+    )

xinference/thirdparty/f5_tts/eval/eval_infer_batch.py

@@ -0,0 +1,207 @@
+import os
+import sys
+
+sys.path.append(os.getcwd())
+
+import argparse
+import time
+from importlib.resources import files
+
+import torch
+import torchaudio
+from accelerate import Accelerator
+from tqdm import tqdm
+
+from f5_tts.eval.utils_eval import (
+    get_inference_prompt,
+    get_librispeech_test_clean_metainfo,
+    get_seedtts_testset_metainfo,
+)
+from f5_tts.infer.utils_infer import load_checkpoint, load_vocoder
+from f5_tts.model import CFM, DiT, UNetT
+from f5_tts.model.utils import get_tokenizer
+
+accelerator = Accelerator()
+device = f"cuda:{accelerator.process_index}"
+
+
+# --------------------- Dataset Settings -------------------- #
+
+target_sample_rate = 24000
+n_mel_channels = 100
+hop_length = 256
+win_length = 1024
+n_fft = 1024
+target_rms = 0.1
+
+rel_path = str(files("f5_tts").joinpath("../../"))
+
+
+def main():
+    # ---------------------- infer setting ---------------------- #
+
+    parser = argparse.ArgumentParser(description="batch inference")
+
+    parser.add_argument("-s", "--seed", default=None, type=int)
+    parser.add_argument("-d", "--dataset", default="Emilia_ZH_EN")
+    parser.add_argument("-n", "--expname", required=True)
+    parser.add_argument("-c", "--ckptstep", default=1200000, type=int)
+    parser.add_argument("-m", "--mel_spec_type", default="vocos", type=str, choices=["bigvgan", "vocos"])
+    parser.add_argument("-to", "--tokenizer", default="pinyin", type=str, choices=["pinyin", "char"])
+
+    parser.add_argument("-nfe", "--nfestep", default=32, type=int)
+    parser.add_argument("-o", "--odemethod", default="euler")
+    parser.add_argument("-ss", "--swaysampling", default=-1, type=float)
+
+    parser.add_argument("-t", "--testset", required=True)
+
+    args = parser.parse_args()
+
+    seed = args.seed
+    dataset_name = args.dataset
+    exp_name = args.expname
+    ckpt_step = args.ckptstep
+    ckpt_path = rel_path + f"/ckpts/{exp_name}/model_{ckpt_step}.pt"
+    mel_spec_type = args.mel_spec_type
+    tokenizer = args.tokenizer
+
+    nfe_step = args.nfestep
+    ode_method = args.odemethod
+    sway_sampling_coef = args.swaysampling
+
+    testset = args.testset
+
+    infer_batch_size = 1  # max frames. 1 for ddp single inference (recommended)
+    cfg_strength = 2.0
+    speed = 1.0
+    use_truth_duration = False
+    no_ref_audio = False
+
+    if exp_name == "F5TTS_Base":
+        model_cls = DiT
+        model_cfg = dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4)
+
+    elif exp_name == "E2TTS_Base":
+        model_cls = UNetT
+        model_cfg = dict(dim=1024, depth=24, heads=16, ff_mult=4)
+
+    if testset == "ls_pc_test_clean":
+        metalst = rel_path + "/data/librispeech_pc_test_clean_cross_sentence.lst"
+        librispeech_test_clean_path = "<SOME_PATH>/LibriSpeech/test-clean"  # test-clean path
+        metainfo = get_librispeech_test_clean_metainfo(metalst, librispeech_test_clean_path)
+
+    elif testset == "seedtts_test_zh":
+        metalst = rel_path + "/data/seedtts_testset/zh/meta.lst"
+        metainfo = get_seedtts_testset_metainfo(metalst)
+
+    elif testset == "seedtts_test_en":
+        metalst = rel_path + "/data/seedtts_testset/en/meta.lst"
+        metainfo = get_seedtts_testset_metainfo(metalst)
+
+    # path to save genereted wavs
+    output_dir = (
+        f"{rel_path}/"
+        f"results/{exp_name}_{ckpt_step}/{testset}/"
+        f"seed{seed}_{ode_method}_nfe{nfe_step}_{mel_spec_type}"
+        f"{f'_ss{sway_sampling_coef}' if sway_sampling_coef else ''}"
+        f"_cfg{cfg_strength}_speed{speed}"
+        f"{'_gt-dur' if use_truth_duration else ''}"
+        f"{'_no-ref-audio' if no_ref_audio else ''}"
+    )
+
+    # -------------------------------------------------#
+
+    use_ema = True
+
+    prompts_all = get_inference_prompt(
+        metainfo,
+        speed=speed,
+        tokenizer=tokenizer,
+        target_sample_rate=target_sample_rate,
+        n_mel_channels=n_mel_channels,
+        hop_length=hop_length,
+        mel_spec_type=mel_spec_type,
+        target_rms=target_rms,
+        use_truth_duration=use_truth_duration,
+        infer_batch_size=infer_batch_size,
+    )
+
+    # Vocoder model
+    local = False
+    if mel_spec_type == "vocos":
+        vocoder_local_path = "../checkpoints/charactr/vocos-mel-24khz"
+    elif mel_spec_type == "bigvgan":
+        vocoder_local_path = "../checkpoints/bigvgan_v2_24khz_100band_256x"
+    vocoder = load_vocoder(vocoder_name=mel_spec_type, is_local=local, local_path=vocoder_local_path)
+
+    # Tokenizer
+    vocab_char_map, vocab_size = get_tokenizer(dataset_name, tokenizer)
+
+    # Model
+    model = CFM(
+        transformer=model_cls(**model_cfg, text_num_embeds=vocab_size, mel_dim=n_mel_channels),
+        mel_spec_kwargs=dict(
+            n_fft=n_fft,
+            hop_length=hop_length,
+            win_length=win_length,
+            n_mel_channels=n_mel_channels,
+            target_sample_rate=target_sample_rate,
+            mel_spec_type=mel_spec_type,
+        ),
+        odeint_kwargs=dict(
+            method=ode_method,
+        ),
+        vocab_char_map=vocab_char_map,
+    ).to(device)
+
+    dtype = torch.float32 if mel_spec_type == "bigvgan" else None
+    model = load_checkpoint(model, ckpt_path, device, dtype=dtype, use_ema=use_ema)
+
+    if not os.path.exists(output_dir) and accelerator.is_main_process:
+        os.makedirs(output_dir)
+
+    # start batch inference
+    accelerator.wait_for_everyone()
+    start = time.time()
+
+    with accelerator.split_between_processes(prompts_all) as prompts:
+        for prompt in tqdm(prompts, disable=not accelerator.is_local_main_process):
+            utts, ref_rms_list, ref_mels, ref_mel_lens, total_mel_lens, final_text_list = prompt
+            ref_mels = ref_mels.to(device)
+            ref_mel_lens = torch.tensor(ref_mel_lens, dtype=torch.long).to(device)
+            total_mel_lens = torch.tensor(total_mel_lens, dtype=torch.long).to(device)
+
+            # Inference
+            with torch.inference_mode():
+                generated, _ = model.sample(
+                    cond=ref_mels,
+                    text=final_text_list,
+                    duration=total_mel_lens,
+                    lens=ref_mel_lens,
+                    steps=nfe_step,
+                    cfg_strength=cfg_strength,
+                    sway_sampling_coef=sway_sampling_coef,
+                    no_ref_audio=no_ref_audio,
+                    seed=seed,
+                )
+                # Final result
+                for i, gen in enumerate(generated):
+                    gen = gen[ref_mel_lens[i] : total_mel_lens[i], :].unsqueeze(0)
+                    gen_mel_spec = gen.permute(0, 2, 1).to(torch.float32)
+                    if mel_spec_type == "vocos":
+                        generated_wave = vocoder.decode(gen_mel_spec).cpu()
+                    elif mel_spec_type == "bigvgan":
+                        generated_wave = vocoder(gen_mel_spec).squeeze(0).cpu()
+
+                    if ref_rms_list[i] < target_rms:
+                        generated_wave = generated_wave * ref_rms_list[i] / target_rms
+                    torchaudio.save(f"{output_dir}/{utts[i]}.wav", generated_wave, target_sample_rate)
+
+    accelerator.wait_for_everyone()
+    if accelerator.is_main_process:
+        timediff = time.time() - start
+        print(f"Done batch inference in {timediff / 60 :.2f} minutes.")
+
+
+if __name__ == "__main__":
+    main()

xinference/thirdparty/f5_tts/eval/eval_infer_batch.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+# e.g. F5-TTS, 16 NFE
+accelerate launch src/f5_tts/eval/eval_infer_batch.py -s 0 -n "F5TTS_Base" -t "seedtts_test_zh" -nfe 16
+accelerate launch src/f5_tts/eval/eval_infer_batch.py -s 0 -n "F5TTS_Base" -t "seedtts_test_en" -nfe 16
+accelerate launch src/f5_tts/eval/eval_infer_batch.py -s 0 -n "F5TTS_Base" -t "ls_pc_test_clean" -nfe 16
+
+# e.g. Vanilla E2 TTS, 32 NFE
+accelerate launch src/f5_tts/eval/eval_infer_batch.py -s 0 -n "E2TTS_Base" -t "seedtts_test_zh" -o "midpoint" -ss 0
+accelerate launch src/f5_tts/eval/eval_infer_batch.py -s 0 -n "E2TTS_Base" -t "seedtts_test_en" -o "midpoint" -ss 0
+accelerate launch src/f5_tts/eval/eval_infer_batch.py -s 0 -n "E2TTS_Base" -t "ls_pc_test_clean" -o "midpoint" -ss 0
+
+# etc.

xinference/thirdparty/f5_tts/eval/eval_librispeech_test_clean.py

@@ -0,0 +1,84 @@
+# Evaluate with Librispeech test-clean, ~3s prompt to generate 4-10s audio (the way of valle/voicebox evaluation)
+
+import sys
+import os
+import argparse
+
+sys.path.append(os.getcwd())
+
+import multiprocessing as mp
+from importlib.resources import files
+
+import numpy as np
+
+from f5_tts.eval.utils_eval import (
+    get_librispeech_test,
+    run_asr_wer,
+    run_sim,
+)
+
+rel_path = str(files("f5_tts").joinpath("../../"))
+
+
+def get_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("-e", "--eval_task", type=str, default="wer", choices=["sim", "wer"])
+    parser.add_argument("-l", "--lang", type=str, default="en")
+    parser.add_argument("-g", "--gen_wav_dir", type=str, required=True)
+    parser.add_argument("-p", "--librispeech_test_clean_path", type=str, required=True)
+    parser.add_argument("-n", "--gpu_nums", type=int, default=8, help="Number of GPUs to use")
+    parser.add_argument("--local", action="store_true", help="Use local custom checkpoint directory")
+    return parser.parse_args()
+
+
+def main():
+    args = get_args()
+    eval_task = args.eval_task
+    lang = args.lang
+    librispeech_test_clean_path = args.librispeech_test_clean_path  # test-clean path
+    gen_wav_dir = args.gen_wav_dir
+    metalst = rel_path + "/data/librispeech_pc_test_clean_cross_sentence.lst"
+
+    gpus = list(range(args.gpu_nums))
+    test_set = get_librispeech_test(metalst, gen_wav_dir, gpus, librispeech_test_clean_path)
+
+    ## In LibriSpeech, some speakers utilized varying voice characteristics for different characters in the book,
+    ## leading to a low similarity for the ground truth in some cases.
+    # test_set = get_librispeech_test(metalst, gen_wav_dir, gpus, librispeech_test_clean_path, eval_ground_truth = True)  # eval ground truth
+
+    local = args.local
+    if local:  # use local custom checkpoint dir
+        asr_ckpt_dir = "../checkpoints/Systran/faster-whisper-large-v3"
+    else:
+        asr_ckpt_dir = ""  # auto download to cache dir
+    wavlm_ckpt_dir = "../checkpoints/UniSpeech/wavlm_large_finetune.pth"
+
+    # --------------------------- WER ---------------------------
+    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}%")
+
+    # --------------------------- SIM ---------------------------
+    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}")
+
+
+if __name__ == "__main__":
+    main()