init file

.gitattributes

@@ -33,3 +33,7 @@ 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
+ffmpeg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,14 @@
 ---
-title: Xttsv2
-emoji: 🌖
+title: XTTS
+emoji: 🐸
 colorFrom: green
-colorTo: blue
+colorTo: red
 sdk: gradio
-sdk_version: 4.3.0
+sdk_version: 3.44.3
 app_file: app.py
 pinned: false
+models:
+- coqui/XTTS-v1
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,482 @@
+import sys
+import os,stat
+import subprocess
+import random
+from zipfile import ZipFile
+import uuid 
+
+# By using XTTS you agree to CPML license https://coqui.ai/cpml
+os.environ["COQUI_TOS_AGREED"] = "1"
+
+# langid is used to detect language for longer text
+# Most users expect text to be their own language, there is checkbox to disable it
+import langid 
+
+import gradio as gr
+from TTS.api import TTS
+from TTS.tts.configs.xtts_config import XttsConfig
+from TTS.tts.models.xtts import Xtts
+from TTS.utils.generic_utils import get_user_data_dir
+HF_TOKEN = os.environ.get("HF_TOKEN")
+from huggingface_hub import HfApi
+# will use api to restart space on a unrecoverable error
+api = HfApi(token=HF_TOKEN)
+repo_id = "coqui/xtts"
+
+# Use never ffmpeg binary for Ubuntu20 to use denoising for microphone input
+print("Export newer ffmpeg binary for denoise filter")
+ZipFile("ffmpeg.zip").extractall()
+print("Make ffmpeg binary executable")
+st = os.stat('ffmpeg')
+os.chmod('ffmpeg', st.st_mode | stat.S_IEXEC)
+
+# Load TTS
+from TTS.utils.manage import ModelManager
+import torch
+model_name = "tts_models/multilingual/multi-dataset/xtts_v2"
+ModelManager().download_model(model_name)
+model_path = os.path.join(get_user_data_dir("tts"), model_name.replace("/", "--"))
+print("XTTS downloaded")
+tts = TTS(model_name)
+if torch.cuda.is_available():
+    tts.to("cuda")
+else:
+    tts.to("cpu")
+
+# This is for debugging purposes only
+DEVICE_ASSERT_DETECTED=0
+DEVICE_ASSERT_PROMPT=None
+DEVICE_ASSERT_LANG=None
+
+def predict(prompt, language, audio_file_pth, mic_file_path, use_mic, voice_cleanup, no_lang_auto_detect, agree,):
+    if agree == True:
+        supported_languages=["en","es","fr","de","it","pt","pl","tr","ru","nl","cs","ar","zh-cn","ja","ko","hu"]
+
+        if language not in supported_languages:
+            gr.Warning("Language you put in is not in is not in our Supported Languages, please choose from dropdown")
+                
+            return (
+                    None,
+                    None,
+                    None,
+                ) 
+
+        language_predicted=langid.classify(prompt)[0].strip() # strip need as there is space at end!
+
+        # tts expects chinese as zh-cn
+        if language_predicted == "zh": 
+            #we use zh-cn 
+            language_predicted = "zh-cn"
+        print(f"Detected language:{language_predicted}, Chosen language:{language}")
+
+        # After text character length 15 trigger language detection
+        if len(prompt)>15:
+            # allow any language for short text as some may be common
+            # If user unchecks language autodetection it will not trigger
+            # You may remove this completely for own use
+            if language_predicted != language and not no_lang_auto_detect:
+                #Please duplicate and remove this check if you really want this
+                #Or auto-detector fails to identify language (which it can on pretty short text or mixed text)
+                gr.Warning(f"It looks like your text isn’t the language you chose , if you’re sure the text is the same language you chose, please check disable language auto-detection checkbox" )
+            
+                return (
+                        None,
+                        None,
+                        None,
+                    ) 
+
+        
+        if use_mic == True:
+            if mic_file_path is not None:
+               speaker_wav=mic_file_path
+            else:
+                gr.Warning("Please record your voice with Microphone, or uncheck Use Microphone to use reference audios")
+                return (
+                    None,
+                    None,
+                    None,
+                ) 
+                
+        else:
+            speaker_wav=audio_file_pth
+
+        
+        # Filtering for microphone input, as it has BG noise, maybe silence in beginning and end
+        # This is fast filtering not perfect
+
+        # Apply all on demand
+        lowpassfilter=denoise=trim=loudness=True
+        
+        if lowpassfilter:
+            lowpass_highpass="lowpass=8000,highpass=75," 
+        else:
+            lowpass_highpass=""
+
+        if trim:
+            # better to remove silence in beginning and end for microphone
+            trim_silence="areverse,silenceremove=start_periods=1:start_silence=0:start_threshold=0.02,areverse,silenceremove=start_periods=1:start_silence=0:start_threshold=0.02,"
+        else:
+            trim_silence=""
+            
+        if (voice_cleanup):
+            try:
+                out_filename = speaker_wav + str(uuid.uuid4()) + ".wav"  #ffmpeg to know output format
+    
+                #we will use newer ffmpeg as that has afftn denoise filter
+                shell_command = f"./ffmpeg -y -i {speaker_wav} -af {lowpass_highpass}{trim_silence} {out_filename}".split(" ")
+    
+                command_result = subprocess.run([item for item in shell_command], capture_output=False,text=True, check=True)
+                speaker_wav=out_filename
+                print("Filtered microphone input")
+            except subprocess.CalledProcessError:
+                # There was an error - command exited with non-zero code
+                print("Error: failed filtering, use original microphone input")
+        else:
+            speaker_wav=speaker_wav
+
+        if len(prompt)<2:
+            gr.Warning("Please give a longer prompt text")
+            return (
+                    None,
+                    None,
+                    None,
+                )
+        if len(prompt)>200:
+            gr.Warning("Text length limited to 200 characters for this demo, please try shorter text. You can clone this space and edit code for your own usage")
+            return (
+                    None,
+                    None,
+                    None,
+                )  
+        global DEVICE_ASSERT_DETECTED
+        if DEVICE_ASSERT_DETECTED:
+            global DEVICE_ASSERT_PROMPT
+            global DEVICE_ASSERT_LANG
+            #It will likely never come here as we restart space on first unrecoverable error now
+            print(f"Unrecoverable exception caused by language:{DEVICE_ASSERT_LANG} prompt:{DEVICE_ASSERT_PROMPT}")
+            
+        try:   
+            tts.tts_to_file(
+                text=prompt,
+                file_path="output.wav",
+                language=language,
+                speaker_wav=speaker_wav,
+            )
+        except RuntimeError as e :
+            if "device-side assert" in str(e):
+                # cannot do anything on cuda device side error, need tor estart
+                print(f"Exit due to: Unrecoverable exception caused by language:{language} prompt:{prompt}", flush=True)
+                gr.Warning("Unhandled Exception encounter, please retry in a minute")
+                print("Cuda device-assert Runtime encountered need restart")
+                if not DEVICE_ASSERT_DETECTED:
+                    DEVICE_ASSERT_DETECTED=1
+                    DEVICE_ASSERT_PROMPT=prompt
+                    DEVICE_ASSERT_LANG=language
+
+                
+                # HF Space specific.. This error is unrecoverable need to restart space 
+                api.restart_space(repo_id=repo_id)
+            else:
+                print("RuntimeError: non device-side assert error:", str(e))
+                raise e
+        return (
+            gr.make_waveform(
+                audio="output.wav",
+            ),
+            "output.wav",
+            speaker_wav,
+        )
+    else:
+        gr.Warning("Please accept the Terms & Condition!")
+        return (
+                None,
+                None,
+                None,
+            ) 
+
+
+title = "🐸 XTTSv2 - 3秒语音合成，支持中英双语，告别电音！"
+
+description = f"""
+## <center>🌟 - 只需上传3~10秒语音，支持13种语言，中文能力极大增强！</center>
+### <center>🤗 - 使用[Colab笔记本](https://github.com/KevinWang676/Bark-Voice-Cloning)运行；Powered by [Coqui AI](https://coqui.ai/)</center>
+### <center>🌊 - 更多精彩应用，尽在[滔滔AI](http://www.talktalkai.com)；滔滔AI，为爱滔滔！💕</center>
+### <center>😺️☘️ -  猫尾草修改版 - coqui xTTS v2</center>
+### <center>女声示例 - The booms were tearing at the blocks, the rudder was banging to and fro, and the whole ship creaking, groaning, and jumping like a manufactory.</center>
+### <center>男声示例 - It is a pretty little spot there: a grass plateau, running along by the water's edge, and overhung by willows. </center>
+""".strip()
+
+
+article = """
+<div style='margin:20px auto;'>
+<p>注意❗：请不要生成会对个人以及组织造成侵害的内容，此程序仅供科研、学习及个人娱乐使用。</p>
+<p>🌊🏞️🎶 - 江水东流急，滔滔无尽声。 明·顾璘</p>
+</div>
+"""
+examples = [
+    [
+        "Once when I was six years old I saw a magnificent picture",
+        "en",
+        "examples/female.wav",
+        None,
+        False,
+        False,
+        False,
+        True,
+
+    ],
+    [
+        "Lorsque j'avais six ans j'ai vu, une fois, une magnifique image",
+        "fr",
+        "examples/male.wav",
+        None,
+        False,
+        False,
+        False,
+        True,
+        False,
+    ],
+    [
+        "Als ich sechs war, sah ich einmal ein wunderbares Bild",
+        "de",
+        "examples/female.wav",
+        None,
+        False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "Cuando tenía seis años, vi una vez una imagen magnífica",
+        "es",
+        "examples/male.wav",
+        None,
+        False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "Quando eu tinha seis anos eu vi, uma vez, uma imagem magnífica",
+        "pt",
+        "examples/female.wav",
+        None,
+        False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "Kiedy miałem sześć lat, zobaczyłem pewnego razu wspaniały obrazek",
+        "pl",
+        "examples/male.wav",
+        None,
+        False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "Un tempo lontano, quando avevo sei anni, vidi un magnifico disegno",
+        "it",
+        "examples/female.wav",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "Bir zamanlar, altı yaşındayken, muhteşem bir resim gördüm",
+        "tr",
+        "examples/female.wav",
+        None,
+        False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "Когда мне было шесть лет, я увидел однажды удивительную картинку",
+        "ru",
+        "examples/female.wav",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "Toen ik een jaar of zes was, zag ik op een keer een prachtige plaat",
+        "nl",
+        "examples/male.wav",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "Když mi bylo šest let, viděl jsem jednou nádherný obrázek",
+        "cs",
+        "examples/female.wav",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "当我还只有六岁的时候， 看到了一副精彩的插画",
+        "zh-cn",
+        "examples/female.wav",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+     [
+        "かつて 六歳のとき、素晴らしい絵を見ました",
+        "ja",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+        False,
+        True,
+    ],
+    [
+        "한번은 내가 여섯 살이었을 때 멋진 그림을 보았습니다.",
+        "ko",
+        "examples/female.wav",
+        None,
+        False,
+        True,
+        False,
+        True,
+    ],
+        [
+        "Egyszer hat éves koromban láttam egy csodálatos képet",
+        "hu",
+        "examples/male.wav",
+        None,
+        False,
+        True,
+        False,
+        True,
+    ],
+    [
+        "当我还只有六岁的时候， 看到了一副精彩的插画",
+        "zh-cn",
+        "examples/xiaoxiao(edgetts).mp3",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "当我还只有六岁的时候， 看到了一副精彩的插画",
+        "zh-cn",
+        "examples/jenny(edgetts).mp3",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "当我还只有六岁的时候， 看到了一副精彩的插画",
+        "zh-cn",
+        "examples/xiaoni(edgetts).mp3",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+    [
+        "当我还只有六岁的时候， 看到了一副精彩的插画",
+        "zh-cn",
+        "examples/hsiaochen(edgetts).mp3",
+        None,
+       False,
+        False,
+        False,
+        True,
+    ],
+]
+
+
+
+gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(
+            label="想要合成的文本内容",
+            lines=3,
+            placeholder="想说却还没说的 还很多"
+        ),
+        gr.Dropdown(
+            label="请选择文本内容对应的语言",
+            choices=[
+                "en",
+                "es",
+                "fr",
+                "de",
+                "it",
+                "pt",
+                "pl",
+                "tr",
+                "ru",
+                "nl",
+                "cs",
+                "ar",
+                "zh-cn",
+                "ja",
+                "ko",
+                "hu"
+            ],
+            max_choices=1,
+            value="zh-cn",
+        ),
+        gr.Audio(
+            label="通过文件上传语音",
+            type="filepath",
+            value="examples/female.wav",
+        ),
+        gr.Audio(source="microphone",
+                 type="filepath",
+                 label="使用麦克风上传语音",
+                 info="移动端更稳定，电脑端可能无法上传",
+                 streaming=True,
+                ),
+        gr.Checkbox(label="是否使用麦克风上传语音",
+                    value=False,
+                    info="默认为否",),
+        gr.Checkbox(label="是否需要去除背景音",
+                    value=False,
+                    info="默认为否",
+                    ),
+        gr.Checkbox(label="不使用自动探测语言",
+                    value=False,
+                    info="勾选此选项则不使用自动探测语言",),
+        gr.Checkbox(
+            label="使用条款",
+            value=True,
+            info="我承诺：不会利用此程序生成对个人或组织造成侵害的任何内容",
+        ),
+
+        
+    ],
+    outputs=[
+        gr.Video(label="为您合成的专属音频"),
+        gr.Audio(label="Synthesised Audio", visible=False),
+        gr.Audio(label="Reference Audio Used", visible=False),
+    ],
+    title=title,
+    description=description,
+    article=article,
+    examples=examples,
+).queue().launch(debug=True,show_api=False,server_name="0.0.0.0")

examples/female.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a4fa9a16b6463f852cf9424f72c3d3c87aa83010e89db534c53fcd1ae12c02
+size 1002030

examples/hsiaochen(edgetts).mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a944fcf4f031f20a0be95e14afbd6e83f84aeb5d3b9316dee493dcb13fcf63
+size 49824

examples/jenny(edgetts).mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e84470e6c0d8357ffcb7632139a204f2857fc6493037dcce16953aca6a5b00
+size 51120

examples/male.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937c74afad004937e00d1687c68e02210e0c5d93ac072a7c8aeb9ab573517bb1
+size 762126

examples/xiaoni(edgetts).mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12dc1fb1113b1ad4c051277479e204b55a01b8179b70bbec9e85514d2341881d
+size 46800

examples/xiaoxiao(edgetts).mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7a4c69615343adc14ae4ac3bdca3eeaa11f6282fad9b4890ec0dbc5cbc5107
+size 55584

ffmpeg

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51bbdd978250ff7239d213940ff2c92ea56e7d768e8db98d9cbc4079d82e42dc
+size 78999296

ffmpeg.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c04aa2958762686cf94a3bd1456b4738fd537d19bb0a9b622fc788a5e4ce723
+size 29207056

flagged/Reference Audio Used/3f36a128f046665dafb62f8073ad1e8e20733b83/HoneySelect2 2023-11-12 19-08-54_2023111219272 截取视频-0-100.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8a75d41d92b0dcde3e2625b66b9325bf597567f854d54ecbc16bdc74c252b0
+size 1986092

flagged/Synthesised Audio/0fde6535955565dd9a58df2d06670006bf93100e/output.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1daec472ffdc4813221dd49f758a64333bf29ae3b970297c5c6c221e61514cd5
+size 104524

flagged/log.csv

@@ -0,0 +1,2 @@
+想要合成的文本内容,请选择文本内容对应的语言,通过文件上传语音,使用麦克风上传语音,是否使用麦克风上传语音,是否需要去除背景音,Do not use language auto-detect,使用条款,为您合成的专属音频,Synthesised Audio,Reference Audio Used,flag,username,timestamp
+英特尔在近期展示了其最新的封装技术——EMIB和Foveros，可实现封装上的多个芯片并排连接或以3D的方式堆叠在一起，并拿出了集成16GB三星LPDDR5X-7500高频内存的Meteor Lake CPU成品，可提供120GB/s的内存峰值带宽，远高于目前的DDR5-5200与LPDDR5-6400。,zh-cn,/home/maoweicao/xtts/flagged/通过文件上传语音/a7e3b789d5cc48818fb5f2281c52cfb16d942bad/tmplqyi0alf.mp3,,False,True,False,True,/home/maoweicao/xtts/flagged/为您合成的专属音频/7f3de074c567d9ff798565df2096ffd03b72d791/tmptr9aormm.mp4,/home/maoweicao/xtts/flagged/Synthesised Audio/0fde6535955565dd9a58df2d06670006bf93100e/output.wav,/home/maoweicao/xtts/flagged/Reference Audio Used/3f36a128f046665dafb62f8073ad1e8e20733b83/HoneySelect2 2023-11-12 19-08-54_2023111219272 截取视频-0-100.wav,,,2023-11-15 22:43:40.741877

flagged/为您合成的专属音频/7f3de074c567d9ff798565df2096ffd03b72d791/tmptr9aormm.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39ec58b7a260ed7c74fbbd7830ad143cd1b4c2818747c6bc409352b219da300
+size 32847

flagged/通过文件上传语音/a7e3b789d5cc48818fb5f2281c52cfb16d942bad/tmplqyi0alf.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed8c22469ad5fd1688b9e66a01a2a7c4726df26cc48bc95520f4bd60bb1e643
+size 166125

output.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c0daeb888c2715efdff597043dd0968fbee0a81e6ca81e6e6d7a24875b6d8b
+size 224844

packages.txt

@@ -0,0 +1 @@
+unzip

requirements.txt

@@ -0,0 +1,54 @@
+# Preinstall requirements from TTS 
+numpy==1.22.0;python_version<="3.10"
+numpy==1.24.3;python_version>"3.10"
+cython==0.29.30
+scipy>=1.11.2
+soundfile==0.12.*
+librosa==0.10.*
+scikit-learn==1.3.0
+numba==0.55.1;python_version<"3.9"
+numba==0.57.0;python_version>="3.9"
+inflect==5.6.*
+tqdm==4.64.*
+anyascii==0.3.*
+pyyaml==6.*
+fsspec==2023.6.0 # <= 2023.9.1 makes aux tests fail
+aiohttp==3.8.*
+packaging==23.1
+# deps for examples
+flask==2.*
+# deps for inference
+pysbd==0.3.4
+# deps for notebooks
+umap-learn==0.5.*
+pandas>=1.4,<2.0
+# deps for training
+matplotlib==3.7.*
+# coqui stack
+trainer
+# config management
+coqpit>=0.0.16
+# chinese g2p deps
+jieba
+pypinyin==0.47.1
+# gruut+supported langs
+gruut[de,es,fr]==2.2.3
+# deps for korean
+jamo
+nltk
+g2pkk>=0.1.1
+# deps for bangla
+bangla
+bnnumerizer
+bnunicodenormalizer
+#deps for tortoise
+k_diffusion
+einops==0.6.*
+transformers==4.33.*
+#deps for bark
+encodec==0.1.*
+# deps for XTTS
+unidecode==1.3.*
+langid
+# Install tts
+TTS==0.17.4

requirments2.txt

@@ -0,0 +1,187 @@
+absl-py==2.0.0
+accelerate==0.24.1
+aiofiles==23.2.1
+aiohttp==3.8.6
+aiosignal==1.3.1
+altair==5.1.2
+annotated-types==0.6.0
+anyascii==0.3.2
+anyio==3.7.1
+appdirs==1.4.4
+async-timeout==4.0.3
+attrs==23.1.0
+audioread==3.0.1
+Babel==2.13.1
+bangla==0.0.2
+blinker==1.7.0
+bnnumerizer==0.0.2
+bnunicodenormalizer==0.1.1
+cachetools==5.3.2
+certifi==2022.12.7
+cffi==1.16.0
+charset-normalizer==2.1.1
+clean-fid==0.1.35
+click==8.1.7
+clip-anytorch==2.5.2
+cmake==3.25.0
+colorama==0.4.6
+contourpy==1.2.0
+coqpit==0.0.17
+cutlet==0.3.0
+cycler==0.12.1
+Cython==0.29.30
+dateparser==1.1.8
+decorator==5.1.1
+deepspeed==0.11.1
+docker-pycreds==0.4.0
+docopt==0.6.2
+einops==0.6.1
+encodec==0.1.1
+exceptiongroup==1.1.3
+fastapi==0.104.1
+ffmpy==0.3.1
+filelock==3.9.0
+Flask==2.3.3
+fonttools==4.44.0
+frozenlist==1.4.0
+fsspec==2023.6.0
+ftfy==6.1.1
+fugashi==1.3.0
+g2pkk==0.1.2
+gitdb==4.0.11
+GitPython==3.1.40
+google-auth==2.23.4
+google-auth-oauthlib==1.1.0
+gradio==3.48.0
+gradio_client==0.6.1
+grpcio==1.59.2
+gruut==2.2.3
+gruut-ipa==0.13.0
+gruut-lang-de==2.0.0
+gruut-lang-en==2.0.0
+gruut-lang-es==2.0.0
+gruut-lang-fr==2.0.2
+h11==0.14.0
+hangul-romanize==0.1.0
+hjson==3.1.0
+httpcore==1.0.2
+httpx==0.25.1
+huggingface-hub==0.19.0
+idna==3.4
+imageio==2.32.0
+importlib-resources==6.1.1
+inflect==5.6.0
+itsdangerous==2.1.2
+jaconv==0.3.4
+jamo==0.4.1
+jieba==0.42.1
+Jinja2==3.1.2
+joblib==1.3.2
+jsonlines==1.2.0
+jsonmerge==1.9.2
+jsonschema==4.19.2
+jsonschema-specifications==2023.7.1
+k-diffusion==0.0.16
+kiwisolver==1.4.5
+kornia==0.7.0
+langid==1.1.6
+lazy_loader==0.3
+librosa==0.10.0
+lit==15.0.7
+llvmlite==0.40.1
+Markdown==3.5.1
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+matplotlib==3.7.3
+mdurl==0.1.2
+mecab-python3==1.0.6
+mojimoji==0.0.12
+mpmath==1.3.0
+msgpack==1.0.7
+multidict==6.0.4
+networkx==2.8.8
+ninja==1.11.1.1
+nltk==3.8.1
+num2words==0.5.13
+numba==0.57.0
+numpy==1.22.0
+oauthlib==3.2.2
+orjson==3.9.10
+packaging==23.1
+pandas==1.5.3
+Pillow==9.3.0
+platformdirs==4.0.0
+pooch==1.8.0
+protobuf==4.23.4
+psutil==5.9.6
+py-cpuinfo==9.0.0
+pyasn1==0.5.0
+pyasn1-modules==0.3.0
+pycparser==2.21
+pydantic==1.10.13
+pydantic_core==2.10.1
+pydub==0.25.1
+Pygments==2.16.1
+pynndescent==0.5.10
+pyparsing==3.1.1
+pypinyin==0.47.1
+pysbd==0.3.4
+python-crfsuite==0.9.9
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.30.2
+regex==2023.10.3
+requests==2.28.1
+requests-oauthlib==1.3.1
+resize-right==0.0.2
+rich==13.6.0
+rpds-py==0.12.0
+rsa==4.9
+safetensors==0.4.0
+scikit-image==0.22.0
+scikit-learn==1.3.0
+scipy==1.11.3
+semantic-version==2.10.0
+sentry-sdk==1.35.0
+setproctitle==1.3.3
+shellingham==1.5.4
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soundfile==0.12.1
+soxr==0.3.7
+starlette==0.27.0
+sympy==1.12
+tensorboard==2.15.1
+tensorboard-data-server==0.7.2
+threadpoolctl==3.2.0
+tifffile==2023.9.26
+tokenizers==0.13.3
+tomlkit==0.12.0
+toolz==0.12.0
+torch==1.13.1+cu117
+torchaudio==0.13.1+cu117
+torchdiffeq==0.2.3
+torchsde==0.2.6
+torchvision==0.14.1+cu117
+tqdm==4.64.1
+trainer==0.0.31
+trampoline==0.1.2
+transformers==4.33.3
+triton==2.0.0
+TTS @ git+https://github.com/coqui-ai/tts.git@46d9c27212939aa54b22f9df842c753de67b1f34
+typer==0.9.0
+typing_extensions==4.8.0
+tzlocal==5.2
+umap-learn==0.5.1
+Unidecode==1.3.7
+unidic-lite==1.0.8
+urllib3==1.26.13
+uvicorn==0.24.0.post1
+wandb==0.16.0
+wcwidth==0.2.9
+websockets==11.0.3
+Werkzeug==3.0.1
+yarl==1.9.2