.gitattributes

@@ -1,52 +1,22 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-<<<<<<< HEAD
-*.bin.* filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-=======
 *.bz2 filter=lfs diff=lfs merge=lfs -text
 *.ckpt filter=lfs diff=lfs merge=lfs -text
->>>>>>> 380bf27beacb11ac87bc6ed91aea895f7a7c9d73
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-<<<<<<< HEAD
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-=======
 *.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
 *.npy filter=lfs diff=lfs merge=lfs -text
 *.npz filter=lfs diff=lfs merge=lfs -text
->>>>>>> 380bf27beacb11ac87bc6ed91aea895f7a7c9d73
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-<<<<<<< HEAD
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*.tfevents* filter=lfs diff=lfs merge=lfs -text
-*.db* filter=lfs diff=lfs merge=lfs -text
-*.ark* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-=======
 *.pickle filter=lfs diff=lfs merge=lfs -text
 *.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
@@ -63,5 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-*.EncryptBy4pd filter=lfs diff=lfs merge=lfs -text
+*.EncryptBy4pd filter=lfs diff=lfs merge=lfs -text
->>>>>>> 380bf27beacb11ac87bc6ed91aea895f7a7c9d73

README.md

@@ -1,318 +0,0 @@
----
-tasks:
-- auto-speech-recognition
-domain:
-- audio
-model-type:
-- autoregressive
-frameworks:
-- pytorch
-backbone:
-- transformer/conformer
-metrics:
-- CER
-license: Apache License 2.0
-language: 
-- multilingual
-tags:
-- FunASR
-- Whisper
-datasets:
-  train:
-  - 680,000 hour
-  test:
-  - test
-indexing:
-   results:
-   - task:
-       name: Automatic Speech Recognition
-     dataset:
-       name: 680,000 hour
-     metrics:
-       - type: CER
-         value: 8.53%  # float
-         description: greedy search, withou lm, avg.
-         args: default
-       - type: RTF
-         value: 0.0251  # float
-         description: GPU inference on V100
-         args: batch_size=1
-widgets:
-  - task: auto-speech-recognition
-    model_revision: v2.0.5
-    inputs:
-      - type: audio
-        name: input
-        title: 音频
-    examples:
-      - name: 1
-        title: 示例1
-        inputs:
-          - name: input
-            data: git://example/asr_example.wav
-    inferencespec:
-      cpu: 8 #CPU数量
-      memory: 4096
----
-
-
-# Whisper模型介绍
-
-## <strong>[ModelScope-FunASR](https://github.com/alibaba-damo-academy/FunASR)</strong>
-<strong>[FunASR](https://github.com/alibaba-damo-academy/FunASR)</strong>希望在语音识别方面建立学术研究和工业应用之间的桥梁。通过支持在ModelScope上发布的工业级语音识别模型的训练和微调，研究人员和开发人员可以更方便地进行语音识别模型的研究和生产，并促进语音识别生态系统的发展。
-
-[**最新动态**](https://github.com/alibaba-damo-academy/FunASR#whats-new) 
-| [**环境安装**](https://github.com/alibaba-damo-academy/FunASR#installation)
-| [**介绍文档**](https://alibaba-damo-academy.github.io/FunASR/en/index.html)
-| [**中文教程**](https://github.com/alibaba-damo-academy/FunASR/wiki#funasr%E7%94%A8%E6%88%B7%E6%89%8B%E5%86%8C)
-| [**服务部署**](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime)
-| [**模型库**](https://github.com/alibaba-damo-academy/FunASR/blob/main/docs/model_zoo/modelscope_models.md)
-| [**联系我们**](https://github.com/alibaba-damo-academy/FunASR#contact)
-
-
-## 基于ModelScope进行推理
-
-- 推理支持音频格式如下：
-  - wav文件路径，例如：data/test/audios/asr_example.wav
-  - pcm文件路径，例如：data/test/audios/asr_example.pcm
-  - wav文件url，例如：https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav
-  - wav二进制数据，格式bytes，例如：用户直接从文件里读出bytes数据或者是麦克风录出bytes数据。
-  - 已解析的audio音频，例如：audio, rate = soundfile.read("asr_example_zh.wav")，类型为numpy.ndarray或者torch.Tensor。
-  - wav.scp文件，需符合如下要求：
-
-```sh
-cat wav.scp
-asr_example1  data/test/audios/asr_example1.wav
-asr_example2  data/test/audios/asr_example2.wav
-...
-```
-
-- 若输入格式wav文件url，api调用方式可参考如下范例：
-
-```python
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-inference_pipeline = pipeline(
-    task=Tasks.auto_speech_recognition,
-    model='iic/Whisper-large-v3', model_revision="v2.0.5")
-
-rec_result = inference_pipeline(input='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav', language=None)
-print(rec_result)
-```
-
-- 输入音频为pcm格式，调用api时需要传入音频采样率参数fs，例如：
-
-```python
-rec_result = inference_pipeline(input='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.pcm', fs=16000)
-```
-
-- 输入音频为wav格式，api调用方式可参考如下范例:
-
-```python
-rec_result = inference_pipeline(input'asr_example_zh.wav')
-```
-
-- 若输入格式为文件wav.scp(注：文件名需要以.scp结尾)，可添加 output_dir 参数将识别结果写入文件中，api调用方式可参考如下范例:
-
-```python
-inference_pipeline(input="wav.scp", output_dir='./output_dir')
-```
-识别结果输出路径结构如下：
-
-```sh
-tree output_dir/
-output_dir/
-└── 1best_recog
-    ├── score
-    └── text
-
-1 directory, 3 files
-```
-score：识别路径得分
-
-text：语音识别结果文件
-
-
-- 若输入音频为已解析的audio音频，api调用方式可参考如下范例：
-
-```python
-import soundfile
-
-waveform, sample_rate = soundfile.read("asr_example_zh.wav")
-rec_result = inference_pipeline(input=waveform)
-```
-
-- ASR、VAD、PUNC模型自由组合
-
-可根据使用需求对VAD和PUNC标点模型进行自由组合，使用方式如下：
-```python
-inference_pipeline = pipeline(
-    task=Tasks.auto_speech_recognition,
-    model='iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch', model_revision="v2.0.4",
-    vad_model='iic/speech_fsmn_vad_zh-cn-16k-common-pytorch', vad_model_revision="v2.0.4",
-    punc_model='iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch', punc_model_revision="v2.0.4",
-    # spk_model="iic/speech_campplus_sv_zh-cn_16k-common",
-    # spk_model_revision="v2.0.2",
-)
-```
-若不使用PUNC模型，可配置punc_model=""，或不传入punc_model参数，如需加入LM模型，可增加配置lm_model='damo/speech_transformer_lm_zh-cn-common-vocab8404-pytorch'，并设置lm_weight和beam_size参数。
-
-## 基于FunASR进行推理
-
-下面为快速上手教程，测试音频（[中文](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav)，[英文](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav)）
-
-### 可执行命令行
-在命令行终端执行：
-
-```shell
-funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=vad_example.wav
-```
-
-注：支持单条音频文件识别，也支持文件列表，列表为kaldi风格wav.scp：`wav_id   wav_path`
-
-### python示例
-#### 非实时语音识别
-```python
-from funasr import AutoModel
-# paraformer-zh is a multi-functional asr model
-# use vad, punc, spk or not as you need
-model = AutoModel(model="paraformer-zh", model_revision="v2.0.4",
-                  vad_model="fsmn-vad", vad_model_revision="v2.0.4",
-                  punc_model="ct-punc-c", punc_model_revision="v2.0.4",
-                  # spk_model="cam++", spk_model_revision="v2.0.2",
-                  )
-res = model.generate(input=f"{model.model_path}/example/asr_example.wav", 
-            batch_size_s=300, 
-            hotword='魔搭')
-print(res)
-```
-注：`model_hub`：表示模型仓库，`ms`为选择modelscope下载，`hf`为选择huggingface下载。
-
-#### 实时语音识别
-
-```python
-from funasr import AutoModel
-
-chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
-encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
-decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
-
-model = AutoModel(model="paraformer-zh-streaming", model_revision="v2.0.4")
-
-import soundfile
-import os
-
-wav_file = os.path.join(model.model_path, "example/asr_example.wav")
-speech, sample_rate = soundfile.read(wav_file)
-chunk_stride = chunk_size[1] * 960 # 600ms
-
-cache = {}
-total_chunk_num = int(len((speech)-1)/chunk_stride+1)
-for i in range(total_chunk_num):
-    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
-    is_final = i == total_chunk_num - 1
-    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
-    print(res)
-```
-
-注：`chunk_size`为流式延时配置，`[0,10,5]`表示上屏实时出字粒度为`10*60=600ms`，未来信息为`5*60=300ms`。每次推理输入为`600ms`（采样点数为`16000*0.6=960`），输出为对应文字，最后一个语音片段输入需要设置`is_final=True`来强制输出最后一个字。
-
-#### 语音端点检测（非实时）
-```python
-from funasr import AutoModel
-
-model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
-
-wav_file = f"{model.model_path}/example/asr_example.wav"
-res = model.generate(input=wav_file)
-print(res)
-```
-
-#### 语音端点检测（实时）
-```python
-from funasr import AutoModel
-
-chunk_size = 200 # ms
-model = AutoModel(model="fsmn-vad", model_revision="v2.0.4")
-
-import soundfile
-
-wav_file = f"{model.model_path}/example/vad_example.wav"
-speech, sample_rate = soundfile.read(wav_file)
-chunk_stride = int(chunk_size * sample_rate / 1000)
-
-cache = {}
-total_chunk_num = int(len((speech)-1)/chunk_stride+1)
-for i in range(total_chunk_num):
-    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
-    is_final = i == total_chunk_num - 1
-    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size)
-    if len(res[0]["value"]):
-        print(res)
-```
-
-#### 标点恢复
-```python
-from funasr import AutoModel
-
-model = AutoModel(model="ct-punc", model_revision="v2.0.4")
-
-res = model.generate(input="那今天的会就到这里吧 happy new year 明年见")
-print(res)
-```
-
-#### 时间戳预测
-```python
-from funasr import AutoModel
-
-model = AutoModel(model="fa-zh", model_revision="v2.0.4")
-
-wav_file = f"{model.model_path}/example/asr_example.wav"
-text_file = f"{model.model_path}/example/text.txt"
-res = model.generate(input=(wav_file, text_file), data_type=("sound", "text"))
-print(res)
-```
-
-更多详细用法（[示例](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)）
-
-
-## 微调
-
-详细用法（[示例](https://github.com/alibaba-damo-academy/FunASR/tree/main/examples/industrial_data_pretraining)）
-
-## 使用方式以及适用范围
-
-运行范围
-- 支持Linux-x86_64、Mac和Windows运行。
-
-使用方式
-- 直接推理：可以直接对输入音频进行解码，输出目标文字。
-
-使用范围与目标场景
-- 适合于离线语音识别场景
-
-
-## 模型局限性以及可能的偏差
-
-考虑到特征提取流程和工具以及训练工具差异，会对CER的数据带来一定的差异（<0.1%），推理GPU环境差异导致的RTF数值差异。
-
-
-
-## 相关论文以及引用信息
-
-```BibTeX
-@inproceedings{radford2023robust,
-  title={Robust speech recognition via large-scale weak supervision},
-  author={Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
-  booktitle={International Conference on Machine Learning},
-  pages={28492--28518},
-  year={2023},
-  organization={PMLR}
-}
-```
-
-
-
-
-

config.yaml

@@ -1,38 +0,0 @@
-# network architecture
-model: WhisperWarp
-model_conf:
-    lsm_weight: 0.1
-    length_normalized_loss: true
-    hub: funasr # openai
-
-
-
-# only use for hub == funasr,
-#  if hub == openai, dims is automaticall download
-dims:
-    n_mels: 128
-    n_vocab: 51866
-    n_audio_ctx: 1500
-    n_audio_state: 1280
-    n_audio_head: 20
-    n_audio_layer: 32
-    n_text_ctx: 448
-    n_text_state: 1280
-    n_text_head: 20
-    n_text_layer: 32
-
-# frontend related
-frontend: WhisperFrontend
-frontend_conf:
-    fs: 16000
-    n_mels: ${dims.n_mels}
-    do_pad_trim: true
-
-tokenizer: WhisperTokenizer
-tokenizer_conf:
-  language: null
-  task: transcribe
-  is_multilingual: true
-  num_languages: 100
-
-scope_map: [none, "model."]

configuration.json

@@ -1,12 +0,0 @@
-{
-  "framework": "pytorch",
-  "task" : "auto-speech-recognition",
-  "model": {"type" : "funasr"},
-  "pipeline": {"type":"funasr-pipeline"},
-  "model_name_in_hub": {
-    "ms":"", 
-    "hf":""},
-  "file_path_metas": {
-    "init_param":"large-v3.pt", 
-    "config":"config.yaml"}
-}

requirements.txt

@@ -1 +0,0 @@
-openai-whisper