zhifu gao
2024-03-29 320c7ff2c2dfbce13ee01589a64b515bf2d7857b
Dev gzf new (#1562)

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train

* train
10个文件已修改
1个文件已添加
20个文件已删除
106626 ■■■■■ 已修改文件
README.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
README_zh.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
docs/tutorial/README.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
docs/tutorial/README_zh.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/README.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/README_zh.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/industrial_data_pretraining/paraformer/README.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/industrial_data_pretraining/paraformer/README_zh.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/industrial_data_pretraining/paraformer_streaming/README_zh.md 2 ●●● 补丁 | 查看 | 原始文档 | blame | 历史
examples/industrial_data_pretraining/sense_voice/demo.py 12 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/sense_voice/__init__.py 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/sense_voice/tokenizer.py 444 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/__init__.py 156 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/__main__.py 3 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/assets/gpt2.tiktoken 50256 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/assets/mel_filters.npz 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/assets/multilingual.tiktoken 50257 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/audio.py 157 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/decoding.py 826 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/model.py 314 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/normalizers/__init__.py 2 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/normalizers/basic.py 76 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/normalizers/english.json 1741 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/normalizers/english.py 550 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/timing.py 386 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/tokenizer.py 395 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/transcribe.py 605 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/triton_ops.py 109 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/utils.py 316 ●●●●● 补丁 | 查看 | 原始文档 | blame | 历史
funasr/models/whisper_raw/version.py 1 ●●●● 补丁 | 查看 | 原始文档 | blame | 历史
README.md
@@ -155,7 +155,7 @@
from funasr import AutoModel
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
README_zh.md
@@ -151,7 +151,7 @@
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
docs/tutorial/README.md
@@ -130,7 +130,7 @@
from funasr import AutoModel
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
docs/tutorial/README_zh.md
@@ -131,7 +131,7 @@
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
examples/README.md
@@ -130,7 +130,7 @@
from funasr import AutoModel
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
examples/README_zh.md
@@ -131,7 +131,7 @@
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
examples/industrial_data_pretraining/paraformer-zh-spk/README_zh.md
@@ -131,7 +131,7 @@
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
examples/industrial_data_pretraining/paraformer/README.md
@@ -130,7 +130,7 @@
from funasr import AutoModel
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
examples/industrial_data_pretraining/paraformer/README_zh.md
@@ -131,7 +131,7 @@
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
examples/industrial_data_pretraining/paraformer_streaming/README_zh.md
@@ -131,7 +131,7 @@
model = AutoModel(model="fsmn-vad")
wav_file = f"{model.model_path}/example/asr_example.wav"
wav_file = f"{model.model_path}/example/vad_example.wav"
res = model.generate(input=wav_file)
print(res)
```
examples/industrial_data_pretraining/sense_voice/demo.py
New file
@@ -0,0 +1,12 @@
#!/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)
from funasr import AutoModel
model = AutoModel(model="/Users/zhifu/Downloads/modelscope_models/SenseVoice",
                  )
res = model.generate(input="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav")
print(res)
funasr/models/sense_voice/__init__.py
funasr/models/sense_voice/tokenizer.py
File was deleted
funasr/models/whisper_raw/__init__.py
File was deleted
funasr/models/whisper_raw/__main__.py
File was deleted
funasr/models/whisper_raw/assets/gpt2.tiktoken
File was deleted
funasr/models/whisper_raw/assets/mel_filters.npz
Binary files differ
funasr/models/whisper_raw/assets/multilingual.tiktoken
File was deleted
funasr/models/whisper_raw/audio.py
File was deleted
funasr/models/whisper_raw/decoding.py
File was deleted
funasr/models/whisper_raw/model.py
File was deleted
funasr/models/whisper_raw/normalizers/__init__.py
File was deleted
funasr/models/whisper_raw/normalizers/basic.py
File was deleted
funasr/models/whisper_raw/normalizers/english.json
File was deleted
funasr/models/whisper_raw/normalizers/english.py
File was deleted
funasr/models/whisper_raw/timing.py
File was deleted
funasr/models/whisper_raw/tokenizer.py
File was deleted
funasr/models/whisper_raw/transcribe.py
File was deleted
funasr/models/whisper_raw/triton_ops.py
File was deleted
funasr/models/whisper_raw/utils.py
File was deleted
funasr/models/whisper_raw/version.py
File was deleted