xinference 0.16.3__py3-none-any.whl → 1.2.1__py3-none-any.whl

xinference/thirdparty/f5_tts/configs/E2TTS_Base_train.yaml

@@ -0,0 +1,44 @@
+hydra:
+  run:
+    dir: ckpts/${model.name}_${model.mel_spec.mel_spec_type}_${model.tokenizer}_${datasets.name}/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    
+datasets:
+  name: Emilia_ZH_EN  # dataset name
+  batch_size_per_gpu: 38400  # 8 GPUs, 8 * 38400 = 307200
+  batch_size_type: frame  # "frame" or "sample"
+  max_samples: 64  # max sequences per batch if use frame-wise batch_size. we set 32 for small models, 64 for base models
+  num_workers: 16
+
+optim:
+  epochs: 15
+  learning_rate: 7.5e-5
+  num_warmup_updates: 20000  # warmup steps
+  grad_accumulation_steps: 1  # note: updates = steps / grad_accumulation_steps
+  max_grad_norm: 1.0  # gradient clipping
+  bnb_optimizer: False  # use bnb 8bit AdamW optimizer or not
+
+model:
+  name: E2TTS_Base
+  tokenizer: pinyin
+  tokenizer_path: None  # if tokenizer = 'custom', define the path to the tokenizer you want to use (should be vocab.txt)
+  arch:
+    dim: 1024
+    depth: 24
+    heads: 16
+    ff_mult: 4
+  mel_spec:
+    target_sample_rate: 24000
+    n_mel_channels: 100
+    hop_length: 256
+    win_length: 1024
+    n_fft: 1024
+    mel_spec_type: vocos  # 'vocos' or 'bigvgan'
+  vocoder:
+    is_local: False  # use local offline ckpt or not
+    local_path: None  # local vocoder path
+
+ckpts:
+  logger: wandb  # wandb | tensorboard | None
+  save_per_updates: 50000  # save checkpoint per steps
+  last_per_steps: 5000  # save last checkpoint per steps
+  save_dir: ckpts/${model.name}_${model.mel_spec.mel_spec_type}_${model.tokenizer}_${datasets.name}/${now:%Y-%m-%d}/${now:%H-%M-%S}

xinference/thirdparty/f5_tts/configs/E2TTS_Small_train.yaml

@@ -0,0 +1,44 @@
+hydra:
+  run:
+    dir: ckpts/${model.name}_${model.mel_spec.mel_spec_type}_${model.tokenizer}_${datasets.name}/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    
+datasets:
+  name: Emilia_ZH_EN
+  batch_size_per_gpu: 38400  # 8 GPUs, 8 * 38400 = 307200
+  batch_size_type: frame  # "frame" or "sample"
+  max_samples: 64  # max sequences per batch if use frame-wise batch_size. we set 32 for small models, 64 for base models
+  num_workers: 16
+
+optim:
+  epochs: 15
+  learning_rate: 7.5e-5
+  num_warmup_updates: 20000  # warmup steps
+  grad_accumulation_steps: 1  # note: updates = steps / grad_accumulation_steps
+  max_grad_norm: 1.0
+  bnb_optimizer: False  
+
+model:
+  name: E2TTS_Small
+  tokenizer: pinyin
+  tokenizer_path: None  # if tokenizer = 'custom', define the path to the tokenizer you want to use (should be vocab.txt)
+  arch:
+    dim: 768
+    depth: 20
+    heads: 12
+    ff_mult: 4
+  mel_spec:
+    target_sample_rate: 24000
+    n_mel_channels: 100
+    hop_length: 256
+    win_length: 1024
+    n_fft: 1024
+    mel_spec_type: vocos  # 'vocos' or 'bigvgan'
+  vocoder:
+    is_local: False  # use local offline ckpt or not
+    local_path: None  # local vocoder path
+
+ckpts:
+  logger: wandb  # wandb | tensorboard | None
+  save_per_updates: 50000  # save checkpoint per steps
+  last_per_steps: 5000  # save last checkpoint per steps
+  save_dir: ckpts/${model.name}_${model.mel_spec.mel_spec_type}_${model.tokenizer}_${datasets.name}/${now:%Y-%m-%d}/${now:%H-%M-%S}

xinference/thirdparty/f5_tts/configs/F5TTS_Base_train.yaml

@@ -0,0 +1,46 @@
+hydra:
+  run:
+    dir: ckpts/${model.name}_${model.mel_spec.mel_spec_type}_${model.tokenizer}_${datasets.name}/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    
+datasets:
+  name: Emilia_ZH_EN  # dataset name
+  batch_size_per_gpu: 38400  # 8 GPUs, 8 * 38400 = 307200
+  batch_size_type: frame  # "frame" or "sample"
+  max_samples: 64  # max sequences per batch if use frame-wise batch_size. we set 32 for small models, 64 for base models
+  num_workers: 16
+
+optim:
+  epochs: 15
+  learning_rate: 7.5e-5
+  num_warmup_updates: 20000  # warmup steps
+  grad_accumulation_steps: 1  # note: updates = steps / grad_accumulation_steps
+  max_grad_norm: 1.0  # gradient clipping
+  bnb_optimizer: False  # use bnb 8bit AdamW optimizer or not
+
+model:
+  name: F5TTS_Base  # model name
+  tokenizer: pinyin  # tokenizer type
+  tokenizer_path: None  # if tokenizer = 'custom', define the path to the tokenizer you want to use (should be vocab.txt)
+  arch:
+    dim: 1024
+    depth: 22
+    heads: 16
+    ff_mult: 2
+    text_dim: 512
+    conv_layers: 4
+  mel_spec:
+    target_sample_rate: 24000
+    n_mel_channels: 100
+    hop_length: 256
+    win_length: 1024
+    n_fft: 1024
+    mel_spec_type: vocos  # 'vocos' or 'bigvgan'
+  vocoder:
+    is_local: False  # use local offline ckpt or not
+    local_path: None  # local vocoder path
+
+ckpts:
+  logger: wandb  # wandb | tensorboard | None
+  save_per_updates: 50000  # save checkpoint per steps
+  last_per_steps: 5000  # save last checkpoint per steps
+  save_dir: ckpts/${model.name}_${model.mel_spec.mel_spec_type}_${model.tokenizer}_${datasets.name}/${now:%Y-%m-%d}/${now:%H-%M-%S}

xinference/thirdparty/f5_tts/configs/F5TTS_Small_train.yaml

@@ -0,0 +1,46 @@
+hydra:
+  run:
+    dir: ckpts/${model.name}_${model.mel_spec.mel_spec_type}_${model.tokenizer}_${datasets.name}/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    
+datasets:
+  name: Emilia_ZH_EN
+  batch_size_per_gpu: 38400  # 8 GPUs, 8 * 38400 = 307200
+  batch_size_type: frame  # "frame" or "sample"
+  max_samples: 64  # max sequences per batch if use frame-wise batch_size. we set 32 for small models, 64 for base models
+  num_workers: 16
+
+optim:
+  epochs: 15
+  learning_rate: 7.5e-5
+  num_warmup_updates: 20000  # warmup steps
+  grad_accumulation_steps: 1  # note: updates = steps / grad_accumulation_steps
+  max_grad_norm: 1.0  # gradient clipping
+  bnb_optimizer: False  # use bnb 8bit AdamW optimizer or not
+
+model:
+  name: F5TTS_Small
+  tokenizer: pinyin
+  tokenizer_path: None  # if tokenizer = 'custom', define the path to the tokenizer you want to use (should be vocab.txt)
+  arch:
+    dim: 768
+    depth: 18
+    heads: 12
+    ff_mult: 2
+    text_dim: 512
+    conv_layers: 4
+  mel_spec:
+    target_sample_rate: 24000
+    n_mel_channels: 100
+    hop_length: 256
+    win_length: 1024
+    n_fft: 1024
+    mel_spec_type: vocos  # 'vocos' or 'bigvgan'
+  vocoder:
+    is_local: False  # use local offline ckpt or not
+    local_path: None  # local vocoder path
+
+ckpts:
+  logger: wandb  # wandb | tensorboard | None
+  save_per_updates: 50000  # save checkpoint per steps
+  last_per_steps: 5000  # save last checkpoint per steps
+  save_dir: ckpts/${model.name}_${model.mel_spec.mel_spec_type}_${model.tokenizer}_${datasets.name}/${now:%Y-%m-%d}/${now:%H-%M-%S}

xinference/thirdparty/f5_tts/eval/README.md

@@ -0,0 +1,49 @@
+
+# Evaluation
+
+Install packages for evaluation:
+
+```bash
+pip install -e .[eval]
+```
+
+## Generating Samples for Evaluation
+
+### Prepare Test Datasets
+
+1. *Seed-TTS testset*: Download from [seed-tts-eval](https://github.com/BytedanceSpeech/seed-tts-eval).
+2. *LibriSpeech test-clean*: Download from [OpenSLR](http://www.openslr.org/12/).
+3. Unzip the downloaded datasets and place them in the `data/` directory.
+4. Update the path for *LibriSpeech test-clean* data in `src/f5_tts/eval/eval_infer_batch.py`
+5. Our filtered LibriSpeech-PC 4-10s subset: `data/librispeech_pc_test_clean_cross_sentence.lst`
+
+### Batch Inference for Test Set
+
+To run batch inference for evaluations, execute the following commands:
+
+```bash
+# batch inference for evaluations
+accelerate config  # if not set before
+bash src/f5_tts/eval/eval_infer_batch.sh
+```
+
+## Objective Evaluation on Generated Results
+
+### Download Evaluation Model Checkpoints
+
+1. Chinese ASR Model: [Paraformer-zh](https://huggingface.co/funasr/paraformer-zh)
+2. English ASR Model: [Faster-Whisper](https://huggingface.co/Systran/faster-whisper-large-v3)
+3. WavLM Model: Download from [Google Drive](https://drive.google.com/file/d/1-aE1NfzpRCLxA4GUxX9ITI3F9LlbtEGP/view).
+
+Then update in the following scripts with the paths you put evaluation model ckpts to.
+
+### Objective Evaluation
+
+Update the path with your batch-inferenced results, and carry out WER / SIM evaluations:
+```bash
+# Evaluation for Seed-TTS test set
+python src/f5_tts/eval/eval_seedtts_testset.py --gen_wav_dir <GEN_WAVE_DIR>
+
+# Evaluation for LibriSpeech-PC test-clean (cross-sentence)
+python src/f5_tts/eval/eval_librispeech_test_clean.py --gen_wav_dir <GEN_WAVE_DIR> --librispeech_test_clean_path <TEST_CLEAN_PATH>
+```

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,
+    )