Text-to-Speech
English
hexgrad commited on
Commit
09f3623
·
verified ·
1 Parent(s): 46c94e3

Upload 2 files

Browse files
Files changed (2) hide show
  1. README.md +7 -4
  2. VOICES.md +10 -0
README.md CHANGED
@@ -24,7 +24,7 @@ pipeline_tag: text-to-speech
24
 
25
  | Model | Published | Training Data | Compute (A100 80GB) | Langs & Voices | SHA256 |
26
  | ----- | --------- | ------------- | ------------------- | -------------- | ------ |
27
- | **v1.0** | **2025 Jan 27** | **Few hundred hrs** | **$1000 for 1000 hrs** | [**5 & 44**](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) | `496dba11` |
28
  | [v0.19](https://huggingface.co/hexgrad/kLegacy/tree/main/v0.19) | 2024 Dec 25 | <100 hrs | $400 for 500 hrs | 1 & 10 | `3b0c392f` |
29
 
30
  ### Usage
@@ -37,13 +37,15 @@ You can run this cell on [Google Colab](https://colab.research.google.com/).
37
  !pip install -q kokoro>=0.3.1 soundfile
38
  # 2️⃣ Install espeak, used for English OOD fallback and some non-English languages
39
  !apt-get -qq -y install espeak-ng > /dev/null 2>&1
 
 
 
40
 
41
  # 3️⃣ Initalize a pipeline
42
  from kokoro import KPipeline
43
  from IPython.display import display, Audio
44
  import soundfile as sf
45
  # 🇺🇸 'a' => American English, 🇬🇧 'b' => British English
46
- # 🇫🇷 'f' => French, 🇮🇳 'h' => Hindi: apt-get install espeak-ng
47
  # 🇯🇵 'j' => Japanese: pip install misaki[ja]
48
  # 🇨🇳 'z' => Mandarin Chinese: pip install misaki[zh]
49
  pipeline = KPipeline(lang_code='a') # <= make sure lang_code matches voice
@@ -56,10 +58,11 @@ It was a Sprawl voice and a Sprawl joke. The Chatsubo was a bar for professional
56
 
57
  These were to have an enormous impact, not only because they were associated with Constantine, but also because, as in so many other areas, the decisions taken by Constantine (or in his name) were to have great significance for centuries to come. One of the main issues was the shape that Christian churches were to take, since there was not, apparently, a tradition of monumental church buildings when Constantine decided to help the Christian church build a series of truly spectacular structures. The main form that these churches took was that of the basilica, a multipurpose rectangular structure, based ultimately on the earlier Greek stoa, which could be found in most of the great cities of the empire. Christianity, unlike classical polytheism, needed a large interior space for the celebration of its religious services, and the basilica aptly filled that need. We naturally do not know the degree to which the emperor was involved in the design of new churches, but it is tempting to connect this with the secular basilica that Constantine completed in the Roman forum (the so-called Basilica of Maxentius) and the one he probably built in Trier, in connection with his residence in the city at a time when he was still caesar.
58
  '''
59
- # text = 'Le dromadaire resplendissant déambulait tranquillement dans les méandres en mastiquant de petites feuilles vernissées.'
60
- # text = 'ट्रांसपोर्टरों की हड़ताल लगातार पांचवें दिन जारी, दिसंबर से इलेक्ट्रॉनिक टोल कलेक्शनल सिस्टम'
61
  # text = '「もしおれがただ偶然、そしてこうしようというつもりでなくここに立っているのなら、ちょっとばかり絶望するところだな」と、そんなことが彼の頭に思い浮かんだ。'
62
  # text = '中國人民不信邪也不怕邪,不惹事也不怕事,任何外國不要指望我們會拿自己的核心利益做交易,不要指望我們會吞下損害我國主權、安全、發展利益的苦果!'
 
 
 
63
 
64
  # 4️⃣ Generate, display, and save audio files in a loop.
65
  generator = pipeline(
 
24
 
25
  | Model | Published | Training Data | Compute (A100 80GB) | Langs & Voices | SHA256 |
26
  | ----- | --------- | ------------- | ------------------- | -------------- | ------ |
27
+ | **v1.0** | **2025 Jan 27** | **Few hundred hrs** | **$1000 for 1000 hrs** | [**6 & 46**](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) | `496dba11` |
28
  | [v0.19](https://huggingface.co/hexgrad/kLegacy/tree/main/v0.19) | 2024 Dec 25 | <100 hrs | $400 for 500 hrs | 1 & 10 | `3b0c392f` |
29
 
30
  ### Usage
 
37
  !pip install -q kokoro>=0.3.1 soundfile
38
  # 2️⃣ Install espeak, used for English OOD fallback and some non-English languages
39
  !apt-get -qq -y install espeak-ng > /dev/null 2>&1
40
+ # 🇫🇷 'f' => French fr-fr
41
+ # 🇮🇳 'h' => Hindi hi
42
+ # 🇮🇹 'i' => Italian it
43
 
44
  # 3️⃣ Initalize a pipeline
45
  from kokoro import KPipeline
46
  from IPython.display import display, Audio
47
  import soundfile as sf
48
  # 🇺🇸 'a' => American English, 🇬🇧 'b' => British English
 
49
  # 🇯🇵 'j' => Japanese: pip install misaki[ja]
50
  # 🇨🇳 'z' => Mandarin Chinese: pip install misaki[zh]
51
  pipeline = KPipeline(lang_code='a') # <= make sure lang_code matches voice
 
58
 
59
  These were to have an enormous impact, not only because they were associated with Constantine, but also because, as in so many other areas, the decisions taken by Constantine (or in his name) were to have great significance for centuries to come. One of the main issues was the shape that Christian churches were to take, since there was not, apparently, a tradition of monumental church buildings when Constantine decided to help the Christian church build a series of truly spectacular structures. The main form that these churches took was that of the basilica, a multipurpose rectangular structure, based ultimately on the earlier Greek stoa, which could be found in most of the great cities of the empire. Christianity, unlike classical polytheism, needed a large interior space for the celebration of its religious services, and the basilica aptly filled that need. We naturally do not know the degree to which the emperor was involved in the design of new churches, but it is tempting to connect this with the secular basilica that Constantine completed in the Roman forum (the so-called Basilica of Maxentius) and the one he probably built in Trier, in connection with his residence in the city at a time when he was still caesar.
60
  '''
 
 
61
  # text = '「もしおれがただ偶然、そしてこうしようというつもりでなくここに立っているのなら、ちょっとばかり絶望するところだな」と、そんなことが彼の頭に思い浮かんだ。'
62
  # text = '中國人民不信邪也不怕邪,不惹事也不怕事,任何外國不要指望我們會拿自己的核心利益做交易,不要指望我們會吞下損害我國主權、安全、發展利益的苦果!'
63
+ # text = 'Le dromadaire resplendissant déambulait tranquillement dans les méandres en mastiquant de petites feuilles vernissées.'
64
+ # text = 'ट्रांसपोर्टरों की हड़ताल लगातार पांचवें दिन जारी, दिसंबर से इलेक्ट्रॉनिक टोल कलेक्शनल सिस्टम'
65
+ # text = "Allora cominciava l'insonnia, o un dormiveglia peggiore dell'insonnia, che talvolta assumeva i caratteri dell'incubo."
66
 
67
  # 4️⃣ Generate, display, and save audio files in a loop.
68
  generator = pipeline(
VOICES.md CHANGED
@@ -76,6 +76,16 @@ Subjectively, voices will sound better or worse to different people.
76
  | hm_omega | 🚹 | B | MM minutes | C | `b55f02a8` |
77
  | hm_psi | 🚹 | B | MM minutes | C | `2f0f055c` |
78
 
 
 
 
 
 
 
 
 
 
 
79
  ### Japanese 🇯🇵
80
 
81
  - [`misaki[ja]`](https://github.com/hexgrad/misaki)
 
76
  | hm_omega | 🚹 | B | MM minutes | C | `b55f02a8` |
77
  | hm_psi | 🚹 | B | MM minutes | C | `2f0f055c` |
78
 
79
+ ### Italian 🇮🇳
80
+
81
+ - espeak-ng `it`
82
+ - Total Italian training data: H hours
83
+
84
+ | Name | Traits | Target Quality | Training Duration | Overall Grade | SHA256 |
85
+ | ---- | ------ | -------------- | ----------------- | ------------- | ------ |
86
+ | if_sara | 🚺 | B | MM minutes | C | `6c0b253b` |
87
+ | im_nicola | 🚹 | B | MM minutes | C | `234ed066` |
88
+
89
  ### Japanese 🇯🇵
90
 
91
  - [`misaki[ja]`](https://github.com/hexgrad/misaki)