From 21dbd460b28c1158a0af95afd583b5057ff5741b Mon Sep 17 00:00:00 2001 From: aceforeverd Date: Thu, 28 Aug 2025 19:00:03 +0800 Subject: [PATCH] first revise --- Dockerfile | 12 + Dockerfile.funasr-mr100 | 20 - README.md | 17 +- replaced_files/mr_v100/cif_predictor.py | 762 ------------------------ test_funasr.py | 28 +- 5 files changed, 30 insertions(+), 809 deletions(-) create mode 100644 Dockerfile delete mode 100644 Dockerfile.funasr-mr100 delete mode 100644 replaced_files/mr_v100/cif_predictor.py diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000..7224fbd --- /dev/null +++ b/Dockerfile @@ -0,0 +1,12 @@ +FROM git.modelhub.org.cn:9443/enginex-metax/maca-c500-pytorch:2.33.0.6-torch2.6-py310-ubuntu24.04-amd64 + +RUN /opt/conda/bin/pip install funasr modelscope huggingface_hub + +RUN chmod 1777 -R /tmp && apt update && apt install -y ffmpeg + +WORKDIR /opt/app +COPY ./ ./ +RUN /opt/conda/bin/pip install -r requirements.txt + +EXPOSE 80 +ENTRYPOINT ["python3", "./test_funasr.py"] diff --git a/Dockerfile.funasr-mr100 b/Dockerfile.funasr-mr100 deleted file mode 100644 index 8a7c0eb..0000000 --- a/Dockerfile.funasr-mr100 +++ /dev/null @@ -1,20 +0,0 @@ -FROM git.modelhub.org.cn:9443/enginex-iluvatar/mr100_corex:4.3.0 - -WORKDIR /root - -COPY requirements.txt /root -RUN pip install -r requirements.txt - -RUN apt update && apt install -y vim net-tools - -RUN pip install funasr==1.2.6 openai-whisper - -ADD . /root/ -ADD nltk_data.tar.gz /root/ -RUN tar -xvzf nltk_data.tar.gz - -RUN cp ./replaced_files/mr_v100/cif_predictor.py /usr/local/lib/python3.10/site-packages/funasr/models/paraformer/ - -EXPOSE 80 -ENTRYPOINT ["bash"] -CMD ["./start_funasr.sh"] \ No newline at end of file diff --git a/README.md b/README.md index 65f5bf7..3cf730f 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,8 @@ -# 天数智芯 智铠100 FunASR +# 沐曦 MetaX C500 FunASR ## 镜像构造 ```shell -docker build -f ./Dockerfile.funasr-mr100 -t . +docker build -t . ``` ## 使用说明 @@ -11,9 +11,8 @@ docker build -f ./Dockerfile.funasr-mr100 -t . 1. 本项目中附带上了示例测试数据，音频文件为`lei-jun-test.wav`，音频的识别准确内容文件为`lei-jun.txt`，用户需要准备好相应的ASR模型路径，本例中假设我们已经下载好了SenseVoiceSmall模型存放于/model/SenseVoiceSmall 2. 在本项目路径下执行以下快速测试命令 ```shell -docker run -it \ - -v /usr/src:/usr/src \ - -v /lib/modules:/lib/modules --device=/dev/iluvatar0:/dev/iluvatar0 \ +metax-docker run -it \ + --gpus=[0] \ -v $PWD:/tmp/workspace \ -v /model:/model \ -e MODEL_DIR=/model/SenseVoiceSmall \ @@ -21,7 +20,7 @@ docker run -it \ -e ANSWER_FILE=lei-jun.txt \ -e RESULT_FILE=result.json \ --cpus=4 --memory=16g \ - + ``` 上述测试指令成功运行将会在terminal中看到对测试音频的识别结果，运行时间以及1-cer效果指标，并且当前文件下会生成一个`result.json`文件记录刚才的测试结果 @@ -29,8 +28,8 @@ docker run -it \ 用户可使用类似上述的docker run指令以交互形式进入镜像中，主要的测试代码为`test_funasr.py`,用户可自行修改代码中需要测试的模型路径、测试文件路径以及调用funASR逻辑 -## 智铠100模型适配情况 -我们在智铠100上针对funASR部分进行了所有大类的适配，测试方式为在Nvidia A100环境下和智铠100加速卡上对同一段长音频进行语音识别任务，获取运行时间，1-cer指标。运行时都只使用一张显卡 +## MetaX C500 模型适配情况 +我们在 MetaX C500 上针对funASR部分进行了所有大类的适配，测试方式为在Nvidia A100环境下和智铠100加速卡上对同一段长音频进行语音识别任务，获取运行时间，1-cer指标。运行时都只使用一张显卡 | 模型大类 | 模型地址 |A100运行时间(秒)|智铠100运行时间(秒)|A100 1-cer|智铠100 1-cer| 备注 | |------|---------------|-----|----|-------|-------|---------------------| @@ -38,4 +37,4 @@ docker run -it \ | whisper | https://www.modelscope.cn/models/iic/Whisper-large-v3 | 23.8337 | 22.9085 | 0.910150 | 0.910150 | | | paraformer | https://modelscope.cn/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch | 4.7246 | 4.7719 | 0.955075 | 0.955075 | | | conformer | https://www.modelscope.cn/models/iic/speech_conformer_asr_nat-zh-cn-16k-aishell2-vocab5212-pytorch | 95.9631 | 125.8649 | 0.349418 | 0.346090 | | -| uni_asr | https://www.modelscope.cn/models/iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline | 70.5289 | 88.9481 | 0.717138 | 0.717138 | 该部分的适配修改了一些funASR源码 | \ No newline at end of file +| uni_asr | https://www.modelscope.cn/models/iic/speech_UniASR-large_asr_2pass-zh-cn-16k-common-vocab8358-tensorflow1-offline | 70.5289 | 88.9481 | 0.717138 | 0.717138 | 该部分的适配修改了一些funASR源码 | diff --git a/replaced_files/mr_v100/cif_predictor.py b/replaced_files/mr_v100/cif_predictor.py deleted file mode 100644 index 9b19ba9..0000000 --- a/replaced_files/mr_v100/cif_predictor.py +++ /dev/null @@ -1,762 +0,0 @@ -#!/usr/bin/env python3 -# -*- encoding: utf-8 -*- -# Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved. -# MIT License (https://opensource.org/licenses/MIT) - -import torch -import logging -import numpy as np - -from funasr.register import tables -from funasr.train_utils.device_funcs import to_device -from funasr.models.transformer.utils.nets_utils import make_pad_mask -from torch.cuda.amp import autocast - - -@tables.register("predictor_classes", "CifPredictor") -class CifPredictor(torch.nn.Module): - def __init__( - self, - idim, - l_order, - r_order, - threshold=1.0, - dropout=0.1, - smooth_factor=1.0, - noise_threshold=0, - tail_threshold=0.45, - ): - super().__init__() - - self.pad = torch.nn.ConstantPad1d((l_order, r_order), 0) - self.cif_conv1d = torch.nn.Conv1d(idim, idim, l_order + r_order + 1, groups=idim) - self.cif_output = torch.nn.Linear(idim, 1) - self.dropout = torch.nn.Dropout(p=dropout) - self.threshold = threshold - self.smooth_factor = smooth_factor - self.noise_threshold = noise_threshold - self.tail_threshold = tail_threshold - - def forward( - self, - hidden, - target_label=None, - mask=None, - ignore_id=-1, - mask_chunk_predictor=None, - target_label_length=None, - ): - - with autocast(False): - h = hidden - context = h.transpose(1, 2) - queries = self.pad(context) - memory = self.cif_conv1d(queries) - output = memory + context - output = self.dropout(output) - output = output.transpose(1, 2) - output = torch.relu(output) - output = self.cif_output(output) - alphas = torch.sigmoid(output) - alphas = torch.nn.functional.relu(alphas * self.smooth_factor - self.noise_threshold) - if mask is not None: - mask = mask.transpose(-1, -2).float() - alphas = alphas * mask - if mask_chunk_predictor is not None: - alphas = alphas * mask_chunk_predictor - alphas = alphas.squeeze(-1) - mask = mask.squeeze(-1) - if target_label_length is not None: - target_length = target_label_length - elif target_label is not None: - target_length = (target_label != ignore_id).float().sum(-1) - else: - target_length = None - token_num = alphas.sum(-1) - if target_length is not None: - alphas *= (target_length / token_num)[:, None].repeat(1, alphas.size(1)) - elif self.tail_threshold > 0.0: - hidden, alphas, token_num = self.tail_process_fn( - hidden, alphas, token_num, mask=mask - ) - - acoustic_embeds, cif_peak = cif(hidden, alphas, self.threshold) - - if target_length is None and self.tail_threshold > 0.0: - token_num_int = torch.max(token_num).type(torch.int32).item() - acoustic_embeds = acoustic_embeds[:, :token_num_int, :] - - return acoustic_embeds, token_num, alphas, cif_peak - - def tail_process_fn(self, hidden, alphas, token_num=None, mask=None): - b, t, d = hidden.size() - tail_threshold = self.tail_threshold - if mask is not None: - zeros_t = torch.zeros((b, 1), dtype=torch.float32, device=alphas.device) - ones_t = torch.ones_like(zeros_t) - mask_1 = torch.cat([mask, zeros_t], dim=1) - mask_2 = torch.cat([ones_t, mask], dim=1) - mask = mask_2 - mask_1 - tail_threshold = mask * tail_threshold - alphas = torch.cat([alphas, zeros_t], dim=1) - alphas = torch.add(alphas, tail_threshold) - else: - tail_threshold = torch.tensor([tail_threshold], dtype=alphas.dtype).to(alphas.device) - tail_threshold = torch.reshape(tail_threshold, (1, 1)) - alphas = torch.cat([alphas, tail_threshold], dim=1) - zeros = torch.zeros((b, 1, d), dtype=hidden.dtype).to(hidden.device) - hidden = torch.cat([hidden, zeros], dim=1) - token_num = alphas.sum(dim=-1) - token_num_floor = torch.floor(token_num) - - return hidden, alphas, token_num_floor - - def gen_frame_alignments( - self, alphas: torch.Tensor = None, encoder_sequence_length: torch.Tensor = None - ): - batch_size, maximum_length = alphas.size() - int_type = torch.int32 - - is_training = self.training - if is_training: - token_num = torch.round(torch.sum(alphas, dim=1)).type(int_type) - else: - token_num = torch.floor(torch.sum(alphas, dim=1)).type(int_type) - - max_token_num = torch.max(token_num).item() - - alphas_cumsum = torch.cumsum(alphas, dim=1) - alphas_cumsum = torch.floor(alphas_cumsum).type(int_type) - alphas_cumsum = alphas_cumsum[:, None, :].repeat(1, max_token_num, 1) - - index = torch.ones([batch_size, max_token_num], dtype=int_type) - index = torch.cumsum(index, dim=1) - index = index[:, :, None].repeat(1, 1, maximum_length).to(alphas_cumsum.device) - - index_div = torch.floor(torch.true_divide(alphas_cumsum, index)).type(int_type) - index_div_bool_zeros = index_div.eq(0) - index_div_bool_zeros_count = torch.sum(index_div_bool_zeros, dim=-1) + 1 - index_div_bool_zeros_count = torch.clamp( - index_div_bool_zeros_count, 0, encoder_sequence_length.max() - ) - token_num_mask = (~make_pad_mask(token_num, maxlen=max_token_num)).to(token_num.device) - index_div_bool_zeros_count *= token_num_mask - - index_div_bool_zeros_count_tile = index_div_bool_zeros_count[:, :, None].repeat( - 1, 1, maximum_length - ) - ones = torch.ones_like(index_div_bool_zeros_count_tile) - zeros = torch.zeros_like(index_div_bool_zeros_count_tile) - ones = torch.cumsum(ones, dim=2) - cond = index_div_bool_zeros_count_tile == ones - index_div_bool_zeros_count_tile = torch.where(cond, zeros, ones) - - index_div_bool_zeros_count_tile_bool = index_div_bool_zeros_count_tile.type(torch.bool) - index_div_bool_zeros_count_tile = 1 - index_div_bool_zeros_count_tile_bool.type(int_type) - index_div_bool_zeros_count_tile_out = torch.sum(index_div_bool_zeros_count_tile, dim=1) - index_div_bool_zeros_count_tile_out = index_div_bool_zeros_count_tile_out.type(int_type) - predictor_mask = ( - (~make_pad_mask(encoder_sequence_length, maxlen=encoder_sequence_length.max())) - .type(int_type) - .to(encoder_sequence_length.device) - ) - index_div_bool_zeros_count_tile_out = index_div_bool_zeros_count_tile_out * predictor_mask - - predictor_alignments = index_div_bool_zeros_count_tile_out - predictor_alignments_length = predictor_alignments.sum(-1).type( - encoder_sequence_length.dtype - ) - return predictor_alignments.detach(), predictor_alignments_length.detach() - - -@tables.register("predictor_classes", "CifPredictorV2") -class CifPredictorV2(torch.nn.Module): - def __init__( - self, - idim, - l_order, - r_order, - threshold=1.0, - dropout=0.1, - smooth_factor=1.0, - noise_threshold=0, - tail_threshold=0.0, - tf2torch_tensor_name_prefix_torch="predictor", - tf2torch_tensor_name_prefix_tf="seq2seq/cif", - tail_mask=True, - ): - super().__init__() - - self.pad = torch.nn.ConstantPad1d((l_order, r_order), 0) - self.cif_conv1d = torch.nn.Conv1d(idim, idim, l_order + r_order + 1) - self.cif_output = torch.nn.Linear(idim, 1) - self.dropout = torch.nn.Dropout(p=dropout) - self.threshold = threshold - self.smooth_factor = smooth_factor - self.noise_threshold = noise_threshold - self.tail_threshold = tail_threshold - self.tf2torch_tensor_name_prefix_torch = tf2torch_tensor_name_prefix_torch - self.tf2torch_tensor_name_prefix_tf = tf2torch_tensor_name_prefix_tf - self.tail_mask = tail_mask - - def forward( - self, - hidden, - target_label=None, - mask=None, - ignore_id=-1, - mask_chunk_predictor=None, - target_label_length=None, - ): - - with autocast(False): - h = hidden - context = h.transpose(1, 2) - queries = self.pad(context) - output = torch.relu(self.cif_conv1d(queries)) - output = output.transpose(1, 2) - - output = self.cif_output(output) - alphas = torch.sigmoid(output) - alphas = torch.nn.functional.relu(alphas * self.smooth_factor - self.noise_threshold) - if mask is not None: - mask = mask.transpose(-1, -2).float() - alphas = alphas * mask - if mask_chunk_predictor is not None: - alphas = alphas * mask_chunk_predictor - alphas = alphas.squeeze(-1) - mask = mask.squeeze(-1) - if target_label_length is not None: - target_length = target_label_length.squeeze(-1) - elif target_label is not None: - target_length = (target_label != ignore_id).float().sum(-1) - else: - target_length = None - token_num = alphas.sum(-1) - if target_length is not None: - alphas *= (target_length / token_num)[:, None].repeat(1, alphas.size(1)) - elif self.tail_threshold > 0.0: - if self.tail_mask: - hidden, alphas, token_num = self.tail_process_fn( - hidden, alphas, token_num, mask=mask - ) - else: - hidden, alphas, token_num = self.tail_process_fn( - hidden, alphas, token_num, mask=None - ) - - acoustic_embeds, cif_peak = cif_v1(hidden, alphas, self.threshold) - if target_length is None and self.tail_threshold > 0.0: - token_num_int = torch.max(token_num).type(torch.int32).item() - acoustic_embeds = acoustic_embeds[:, :token_num_int, :] - - return acoustic_embeds, token_num, alphas, cif_peak - - def forward_chunk(self, hidden, cache=None, **kwargs): - is_final = kwargs.get("is_final", False) - batch_size, len_time, hidden_size = hidden.shape - h = hidden - context = h.transpose(1, 2) - queries = self.pad(context) - output = torch.relu(self.cif_conv1d(queries)) - output = output.transpose(1, 2) - output = self.cif_output(output) - alphas = torch.sigmoid(output) - alphas = torch.nn.functional.relu(alphas * self.smooth_factor - self.noise_threshold) - - alphas = alphas.squeeze(-1) - - token_length = [] - list_fires = [] - list_frames = [] - cache_alphas = [] - cache_hiddens = [] - - if cache is not None and "chunk_size" in cache: - alphas[:, : cache["chunk_size"][0]] = 0.0 - if not is_final: - alphas[:, sum(cache["chunk_size"][:2]) :] = 0.0 - if cache is not None and "cif_alphas" in cache and "cif_hidden" in cache: - cache["cif_hidden"] = to_device(cache["cif_hidden"], device=hidden.device) - cache["cif_alphas"] = to_device(cache["cif_alphas"], device=alphas.device) - hidden = torch.cat((cache["cif_hidden"], hidden), dim=1) - alphas = torch.cat((cache["cif_alphas"], alphas), dim=1) - if cache is not None and is_final: - tail_hidden = torch.zeros((batch_size, 1, hidden_size), device=hidden.device) - tail_alphas = torch.tensor([[self.tail_threshold]], device=alphas.device) - tail_alphas = torch.tile(tail_alphas, (batch_size, 1)) - hidden = torch.cat((hidden, tail_hidden), dim=1) - alphas = torch.cat((alphas, tail_alphas), dim=1) - - len_time = alphas.shape[1] - for b in range(batch_size): - integrate = 0.0 - frames = torch.zeros((hidden_size), device=hidden.device) - list_frame = [] - list_fire = [] - for t in range(len_time): - alpha = alphas[b][t] - if alpha + integrate < self.threshold: - integrate += alpha - list_fire.append(integrate) - frames += alpha * hidden[b][t] - else: - frames += (self.threshold - integrate) * hidden[b][t] - list_frame.append(frames) - integrate += alpha - list_fire.append(integrate) - integrate -= self.threshold - frames = integrate * hidden[b][t] - - cache_alphas.append(integrate) - if integrate > 0.0: - cache_hiddens.append(frames / integrate) - else: - cache_hiddens.append(frames) - - token_length.append(torch.tensor(len(list_frame), device=alphas.device)) - list_fires.append(list_fire) - list_frames.append(list_frame) - - cache["cif_alphas"] = torch.stack(cache_alphas, axis=0) - cache["cif_alphas"] = torch.unsqueeze(cache["cif_alphas"], axis=0) - cache["cif_hidden"] = torch.stack(cache_hiddens, axis=0) - cache["cif_hidden"] = torch.unsqueeze(cache["cif_hidden"], axis=0) - - max_token_len = max(token_length) - if max_token_len == 0: - return hidden, torch.stack(token_length, 0), None, None - list_ls = [] - for b in range(batch_size): - pad_frames = torch.zeros( - (max_token_len - token_length[b], hidden_size), device=alphas.device - ) - if token_length[b] == 0: - list_ls.append(pad_frames) - else: - list_frames[b] = torch.stack(list_frames[b]) - list_ls.append(torch.cat((list_frames[b], pad_frames), dim=0)) - - cache["cif_alphas"] = torch.stack(cache_alphas, axis=0) - cache["cif_alphas"] = torch.unsqueeze(cache["cif_alphas"], axis=0) - cache["cif_hidden"] = torch.stack(cache_hiddens, axis=0) - cache["cif_hidden"] = torch.unsqueeze(cache["cif_hidden"], axis=0) - return torch.stack(list_ls, 0), torch.stack(token_length, 0), None, None - - def tail_process_fn(self, hidden, alphas, token_num=None, mask=None): - b, t, d = hidden.size() - tail_threshold = self.tail_threshold - if mask is not None: - zeros_t = torch.zeros((b, 1), dtype=torch.float32, device=alphas.device) - ones_t = torch.ones_like(zeros_t) - mask_1 = torch.cat([mask, zeros_t], dim=1) - mask_2 = torch.cat([ones_t, mask], dim=1) - mask = mask_2 - mask_1 - tail_threshold = mask * tail_threshold - alphas = torch.cat([alphas, zeros_t], dim=1) - alphas = torch.add(alphas, tail_threshold) - else: - tail_threshold = torch.tensor([tail_threshold], dtype=alphas.dtype).to(alphas.device) - tail_threshold = torch.reshape(tail_threshold, (1, 1)) - if b > 1: - alphas = torch.cat([alphas, tail_threshold.repeat(b, 1)], dim=1) - else: - alphas = torch.cat([alphas, tail_threshold], dim=1) - zeros = torch.zeros((b, 1, d), dtype=hidden.dtype).to(hidden.device) - hidden = torch.cat([hidden, zeros], dim=1) - token_num = alphas.sum(dim=-1) - token_num_floor = torch.floor(token_num) - - return hidden, alphas, token_num_floor - - def gen_frame_alignments( - self, alphas: torch.Tensor = None, encoder_sequence_length: torch.Tensor = None - ): - batch_size, maximum_length = alphas.size() - int_type = torch.int32 - - is_training = self.training - if is_training: - token_num = torch.round(torch.sum(alphas, dim=1)).type(int_type) - else: - token_num = torch.floor(torch.sum(alphas, dim=1)).type(int_type) - - max_token_num = torch.max(token_num).item() - - alphas_cumsum = torch.cumsum(alphas, dim=1) - alphas_cumsum = torch.floor(alphas_cumsum).type(int_type) - alphas_cumsum = alphas_cumsum[:, None, :].repeat(1, max_token_num, 1) - - index = torch.ones([batch_size, max_token_num], dtype=int_type) - index = torch.cumsum(index, dim=1) - index = index[:, :, None].repeat(1, 1, maximum_length).to(alphas_cumsum.device) - - index_div = torch.floor(torch.true_divide(alphas_cumsum, index)).type(int_type) - index_div_bool_zeros = index_div.eq(0) - index_div_bool_zeros_count = torch.sum(index_div_bool_zeros, dim=-1) + 1 - index_div_bool_zeros_count = torch.clamp( - index_div_bool_zeros_count, 0, encoder_sequence_length.max() - ) - token_num_mask = (~make_pad_mask(token_num, maxlen=max_token_num)).to(token_num.device) - index_div_bool_zeros_count *= token_num_mask - - index_div_bool_zeros_count_tile = index_div_bool_zeros_count[:, :, None].repeat( - 1, 1, maximum_length - ) - ones = torch.ones_like(index_div_bool_zeros_count_tile) - zeros = torch.zeros_like(index_div_bool_zeros_count_tile) - ones = torch.cumsum(ones, dim=2) - cond = index_div_bool_zeros_count_tile == ones - index_div_bool_zeros_count_tile = torch.where(cond, zeros, ones) - - index_div_bool_zeros_count_tile_bool = index_div_bool_zeros_count_tile.type(torch.bool) - index_div_bool_zeros_count_tile = 1 - index_div_bool_zeros_count_tile_bool.type(int_type) - index_div_bool_zeros_count_tile_out = torch.sum(index_div_bool_zeros_count_tile, dim=1) - index_div_bool_zeros_count_tile_out = index_div_bool_zeros_count_tile_out.type(int_type) - predictor_mask = ( - (~make_pad_mask(encoder_sequence_length, maxlen=encoder_sequence_length.max())) - .type(int_type) - .to(encoder_sequence_length.device) - ) - index_div_bool_zeros_count_tile_out = index_div_bool_zeros_count_tile_out * predictor_mask - - predictor_alignments = index_div_bool_zeros_count_tile_out - predictor_alignments_length = predictor_alignments.sum(-1).type( - encoder_sequence_length.dtype - ) - return predictor_alignments.detach(), predictor_alignments_length.detach() - - -@tables.register("predictor_classes", "CifPredictorV2Export") -class CifPredictorV2Export(torch.nn.Module): - def __init__(self, model, **kwargs): - super().__init__() - - self.pad = model.pad - self.cif_conv1d = model.cif_conv1d - self.cif_output = model.cif_output - self.threshold = model.threshold - self.smooth_factor = model.smooth_factor - self.noise_threshold = model.noise_threshold - self.tail_threshold = model.tail_threshold - - def forward( - self, - hidden: torch.Tensor, - mask: torch.Tensor, - ): - alphas, token_num = self.forward_cnn(hidden, mask) - mask = mask.transpose(-1, -2).float() - mask = mask.squeeze(-1) - hidden, alphas, token_num = self.tail_process_fn(hidden, alphas, mask=mask) - acoustic_embeds, cif_peak = cif_v1_export(hidden, alphas, self.threshold) - - return acoustic_embeds, token_num, alphas, cif_peak - - def forward_cnn( - self, - hidden: torch.Tensor, - mask: torch.Tensor, - ): - h = hidden - context = h.transpose(1, 2) - queries = self.pad(context) - output = torch.relu(self.cif_conv1d(queries)) - output = output.transpose(1, 2) - - output = self.cif_output(output) - alphas = torch.sigmoid(output) - alphas = torch.nn.functional.relu(alphas * self.smooth_factor - self.noise_threshold) - mask = mask.transpose(-1, -2).float() - alphas = alphas * mask - alphas = alphas.squeeze(-1) - token_num = alphas.sum(-1) - - return alphas, token_num - - def tail_process_fn(self, hidden, alphas, token_num=None, mask=None): - b, t, d = hidden.size() - tail_threshold = self.tail_threshold - - zeros_t = torch.zeros((b, 1), dtype=torch.float32, device=alphas.device) - ones_t = torch.ones_like(zeros_t) - - mask_1 = torch.cat([mask, zeros_t], dim=1) - mask_2 = torch.cat([ones_t, mask], dim=1) - mask = mask_2 - mask_1 - tail_threshold = mask * tail_threshold - alphas = torch.cat([alphas, zeros_t], dim=1) - alphas = torch.add(alphas, tail_threshold) - - zeros = torch.zeros((b, 1, d), dtype=hidden.dtype).to(hidden.device) - hidden = torch.cat([hidden, zeros], dim=1) - token_num = alphas.sum(dim=-1) - token_num_floor = torch.floor(token_num) - - return hidden, alphas, token_num_floor - - -@torch.jit.script -def cif_v1_export(hidden, alphas, threshold: float): - device = hidden.device - dtype = hidden.dtype - batch_size, len_time, hidden_size = hidden.size() - threshold = torch.tensor([threshold], dtype=alphas.dtype).to(alphas.device) - - frames = torch.zeros(batch_size, len_time, hidden_size, dtype=dtype, device=device) - fires = torch.zeros(batch_size, len_time, dtype=dtype, device=device) - - # prefix_sum = torch.cumsum(alphas, dim=1) - prefix_sum = torch.cumsum(alphas, dim=1, dtype=torch.float64).to( - torch.float32 - ) # cumsum precision degradation cause wrong result in extreme - prefix_sum_floor = torch.floor(prefix_sum) - dislocation_prefix_sum = torch.roll(prefix_sum, 1, dims=1) - dislocation_prefix_sum_floor = torch.floor(dislocation_prefix_sum) - - dislocation_prefix_sum_floor[:, 0] = 0 - dislocation_diff = prefix_sum_floor - dislocation_prefix_sum_floor - - fire_idxs = dislocation_diff > 0 - fires[fire_idxs] = 1 - fires = fires + prefix_sum - prefix_sum_floor - - # prefix_sum_hidden = torch.cumsum(alphas.unsqueeze(-1).tile((1, 1, hidden_size)) * hidden, dim=1) - prefix_sum_hidden = torch.cumsum(alphas.unsqueeze(-1).repeat((1, 1, hidden_size)) * hidden, dim=1) - frames = prefix_sum_hidden[fire_idxs] - shift_frames = torch.roll(frames, 1, dims=0) - - batch_len = fire_idxs.sum(1) - batch_idxs = torch.cumsum(batch_len, dim=0) - shift_batch_idxs = torch.roll(batch_idxs, 1, dims=0) - shift_batch_idxs[0] = 0 - shift_frames[shift_batch_idxs] = 0 - - remains = fires - torch.floor(fires) - # remain_frames = remains[fire_idxs].unsqueeze(-1).tile((1, hidden_size)) * hidden[fire_idxs] - remain_frames = remains[fire_idxs].unsqueeze(-1).repeat((1, hidden_size)) * hidden[fire_idxs] - - shift_remain_frames = torch.roll(remain_frames, 1, dims=0) - shift_remain_frames[shift_batch_idxs] = 0 - - frames = frames - shift_frames + shift_remain_frames - remain_frames - - # max_label_len = batch_len.max() - max_label_len = alphas.sum(dim=-1) - max_label_len = torch.floor(max_label_len).max().to(dtype=torch.int64) - - # frame_fires = torch.zeros(batch_size, max_label_len, hidden_size, dtype=dtype, device=device) - frame_fires = torch.zeros(batch_size, max_label_len, hidden_size, dtype=dtype, device=device) - indices = torch.arange(max_label_len, device=device).expand(batch_size, -1) - frame_fires_idxs = indices < batch_len.unsqueeze(1) - frame_fires[frame_fires_idxs] = frames - return frame_fires, fires - - -@torch.jit.script -def cif_export(hidden, alphas, threshold: float): - batch_size, len_time, hidden_size = hidden.size() - threshold = torch.tensor([threshold], dtype=alphas.dtype).to(alphas.device) - - # loop varss - integrate = torch.zeros([batch_size], dtype=alphas.dtype, device=hidden.device) - frame = torch.zeros([batch_size, hidden_size], dtype=hidden.dtype, device=hidden.device) - # intermediate vars along time - list_fires = [] - list_frames = [] - - for t in range(len_time): - alpha = alphas[:, t] - distribution_completion = ( - torch.ones([batch_size], dtype=alphas.dtype, device=hidden.device) - integrate - ) - - integrate += alpha - list_fires.append(integrate) - - fire_place = integrate >= threshold - integrate = torch.where( - fire_place, - integrate - torch.ones([batch_size], dtype=alphas.dtype, device=hidden.device), - integrate, - ) - cur = torch.where(fire_place, distribution_completion, alpha) - remainds = alpha - cur - - frame += cur[:, None] * hidden[:, t, :] - list_frames.append(frame) - frame = torch.where( - fire_place[:, None].repeat(1, hidden_size), remainds[:, None] * hidden[:, t, :], frame - ) - - fires = torch.stack(list_fires, 1) - frames = torch.stack(list_frames, 1) - - fire_idxs = fires >= threshold - frame_fires = torch.zeros_like(hidden) - max_label_len = frames[0, fire_idxs[0]].size(0) - for b in range(batch_size): - frame_fire = frames[b, fire_idxs[b]] - frame_len = frame_fire.size(0) - frame_fires[b, :frame_len, :] = frame_fire - - if frame_len >= max_label_len: - max_label_len = frame_len - frame_fires = frame_fires[:, :max_label_len, :] - return frame_fires, fires - - -class mae_loss(torch.nn.Module): - - def __init__(self, normalize_length=False): - super(mae_loss, self).__init__() - self.normalize_length = normalize_length - self.criterion = torch.nn.L1Loss(reduction="sum") - - def forward(self, token_length, pre_token_length): - loss_token_normalizer = token_length.size(0) - if self.normalize_length: - loss_token_normalizer = token_length.sum().type(torch.float32) - loss = self.criterion(token_length, pre_token_length) - loss = loss / loss_token_normalizer - return loss - - -def cif(hidden, alphas, threshold): - batch_size, len_time, hidden_size = hidden.size() - - # loop varss - integrate = torch.zeros([batch_size], device=hidden.device) - frame = torch.zeros([batch_size, hidden_size], device=hidden.device) - # intermediate vars along time - list_fires = [] - list_frames = [] - - for t in range(len_time): - alpha = alphas[:, t] - distribution_completion = torch.ones([batch_size], device=hidden.device) - integrate - - integrate += alpha - list_fires.append(integrate) - - fire_place = integrate >= threshold - integrate = torch.where( - fire_place, integrate - torch.ones([batch_size], device=hidden.device), integrate - ) - cur = torch.where(fire_place, distribution_completion, alpha) - remainds = alpha - cur - - frame += cur[:, None] * hidden[:, t, :] - list_frames.append(frame) - frame = torch.where( - fire_place[:, None].repeat(1, hidden_size), remainds[:, None] * hidden[:, t, :], frame - ) - - fires = torch.stack(list_fires, 1) - frames = torch.stack(list_frames, 1) - list_ls = [] - len_labels = torch.round(alphas.sum(-1)).int() - max_label_len = len_labels.max() - for b in range(batch_size): - fire = fires[b, :] - l = torch.index_select(frames[b, :, :], 0, torch.nonzero(fire >= threshold).squeeze()) - pad_l = torch.zeros([max_label_len - l.size(0), hidden_size], device=hidden.device) - list_ls.append(torch.cat([l, pad_l], 0)) - return torch.stack(list_ls, 0), fires - - -def cif_wo_hidden_v1(alphas, threshold, return_fire_idxs=False): - batch_size, len_time = alphas.size() - device = alphas.device - dtype = alphas.dtype - - threshold = torch.tensor([threshold], dtype=alphas.dtype).to(alphas.device) - - fires = torch.zeros(batch_size, len_time, dtype=dtype, device=device) - - if torch.cuda.get_device_name() == "Iluvatar MR-V100": - prefix_sum = torch.cumsum(alphas, dim=1) - else: - prefix_sum = torch.cumsum(alphas, dim=1, dtype=torch.float64).to( - torch.float32 - ) # cumsum precision degradation cause wrong result in extreme - prefix_sum_floor = torch.floor(prefix_sum) - dislocation_prefix_sum = torch.roll(prefix_sum, 1, dims=1) - dislocation_prefix_sum_floor = torch.floor(dislocation_prefix_sum) - - dislocation_prefix_sum_floor[:, 0] = 0 - dislocation_diff = prefix_sum_floor - dislocation_prefix_sum_floor - - fire_idxs = dislocation_diff > 0 - fires[fire_idxs] = 1 - fires = fires + prefix_sum - prefix_sum_floor - if return_fire_idxs: - return fires, fire_idxs - return fires - - -def cif_v1(hidden, alphas, threshold): - fires, fire_idxs = cif_wo_hidden_v1(alphas, threshold, return_fire_idxs=True) - - device = hidden.device - dtype = hidden.dtype - batch_size, len_time, hidden_size = hidden.size() - # frames = torch.zeros(batch_size, len_time, hidden_size, dtype=dtype, device=device) - # prefix_sum_hidden = torch.cumsum(alphas.unsqueeze(-1).tile((1, 1, hidden_size)) * hidden, dim=1) - frames = torch.zeros(batch_size, len_time, hidden_size, dtype=dtype, device=device) - prefix_sum_hidden = torch.cumsum(alphas.unsqueeze(-1).repeat((1, 1, hidden_size)) * hidden, dim=1) - - frames = prefix_sum_hidden[fire_idxs] - shift_frames = torch.roll(frames, 1, dims=0) - - batch_len = fire_idxs.sum(1) - batch_idxs = torch.cumsum(batch_len, dim=0) - shift_batch_idxs = torch.roll(batch_idxs, 1, dims=0) - shift_batch_idxs[0] = 0 - shift_frames[shift_batch_idxs] = 0 - - remains = fires - torch.floor(fires) - # remain_frames = remains[fire_idxs].unsqueeze(-1).tile((1, hidden_size)) * hidden[fire_idxs] - remain_frames = remains[fire_idxs].unsqueeze(-1).repeat((1, hidden_size)) * hidden[fire_idxs] - - shift_remain_frames = torch.roll(remain_frames, 1, dims=0) - shift_remain_frames[shift_batch_idxs] = 0 - - frames = frames - shift_frames + shift_remain_frames - remain_frames - - # max_label_len = batch_len.max() - max_label_len = ( - torch.round(alphas.sum(-1)).int().max() - ) # torch.round to calculate the max length - - # frame_fires = torch.zeros(batch_size, max_label_len, hidden_size, dtype=dtype, device=device) - frame_fires = torch.zeros(batch_size, max_label_len, hidden_size, dtype=dtype, device=device) - indices = torch.arange(max_label_len, device=device).expand(batch_size, -1) - frame_fires_idxs = indices < batch_len.unsqueeze(1) - frame_fires[frame_fires_idxs] = frames - return frame_fires, fires - - -def cif_wo_hidden(alphas, threshold): - batch_size, len_time = alphas.size() - - # loop varss - integrate = torch.zeros([batch_size], device=alphas.device) - # intermediate vars along time - list_fires = [] - - for t in range(len_time): - alpha = alphas[:, t] - - integrate += alpha - list_fires.append(integrate) - - fire_place = integrate >= threshold - integrate = torch.where( - fire_place, - integrate - torch.ones([batch_size], device=alphas.device) * threshold, - integrate, - ) - - fires = torch.stack(list_fires, 1) - return fires diff --git a/test_funasr.py b/test_funasr.py index 4228e47..2513dd9 100644 --- a/test_funasr.py +++ b/test_funasr.py @@ -1,7 +1,7 @@ import os import time -import torchaudio import torch +import torchaudio from funasr import AutoModel from funasr.utils.postprocess_utils import rich_transcription_postprocess from utils.calculate import cal_per_cer @@ -34,18 +34,11 @@ def test_funasr(model_dir, audio_file, answer_file, use_gpu): model_name = os.path.basename(model_dir) model_type = determine_model_type(model_name) - if torch.cuda.get_device_name() == "Iluvatar BI-V100" and model_type == "whisper": - # 天垓100情况下的Whisper需要绕过不支持算子 - torch.backends.cuda.enable_flash_sdp(False) - torch.backends.cuda.enable_mem_efficient_sdp(False) - torch.backends.cuda.enable_math_sdp(True) - # 不使用VAD, punct，spk模型，就测试原始ASR能力 model = AutoModel( model=model_dir, # vad_model="fsmn-vad", # vad_kwargs={"max_single_segment_time": 30000}, - vad_model=None, device="cuda:0" if use_gpu else "cpu", disable_update=True ) @@ -114,14 +107,6 @@ def test_funasr(model_dir, audio_file, answer_file, use_gpu): batch_size_s=300 ) text = res[0]["text"] - # elif model_type == "uni_asr": - # if i == 0: - # os.remove(segment_path) - # continue - # res = model.generate( - # input=segment_path - # ) - # text = res[0]["text"] else: raise RuntimeError("unknown model type") ts2 = time.time() @@ -142,6 +127,13 @@ def test_funasr(model_dir, audio_file, answer_file, use_gpu): return processing_time, acc, generated_text if __name__ == "__main__": + if torch.cuda.is_available(): + cuda_tensor = torch.randn(2, 2, device='cuda:0') + print(f"CUDA device index: {cuda_tensor.get_device()}") + else: + print("CUDA not available") + os._exit(1) + test_result = { "time_cuda": 0, "acc_cuda": 0, @@ -176,5 +168,5 @@ if __name__ == "__main__": json.dump(test_result, fp, ensure_ascii=False, indent=4) # 如果是SUT起来镜像的话，需要加上下面让pod永不停止以迎合k8s deployment, 本地测试以及docker run均不需要 if K8S_TEST: - print(f"Start to sleep indefinitely", flush=True) - time.sleep(100000) \ No newline at end of file + print(f"Start to sleep indefinity", flush=True) + time.sleep(100000)