xinference 1.0.1__py3-none-any.whl → 1.2.1__py3-none-any.whl

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()

xinference/thirdparty/f5_tts/eval/eval_seedtts_testset.py

@@ -0,0 +1,84 @@
+# Evaluate with Seed-TTS testset
+
+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_seed_tts_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", choices=["zh", "en"])
+    parser.add_argument("-g", "--gen_wav_dir", 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
+    gen_wav_dir = args.gen_wav_dir
+    metalst = rel_path + f"/data/seedtts_testset/{lang}/meta.lst"  # seed-tts testset
+
+    # NOTE. paraformer-zh result will be slightly different according to the number of gpus, cuz batchsize is different
+    #       zh 1.254 seems a result of 4 workers wer_seed_tts
+    gpus = list(range(args.gpu_nums))
+    test_set = get_seed_tts_test(metalst, gen_wav_dir, gpus)
+
+    local = args.local
+    if local:  # use local custom checkpoint dir
+        if lang == "zh":
+            asr_ckpt_dir = "../checkpoints/funasr"  # paraformer-zh dir under funasr
+        elif lang == "en":
+            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()