Text-to-Speech
English
hexgrad commited on
Commit
5ffb3a4
·
verified ·
1 Parent(s): 808a4b7

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -3
README.md CHANGED
@@ -23,7 +23,7 @@ pipeline_tag: text-to-speech
23
  | Model | Published | Training Data | Compute (A100 80GB) | Released Voices | Released Langs |
24
  | ----- | --------- | ------------- | ------------------- | --------------- | -------------- |
25
  | v0.19 | 2024 Dec 25 | <100 hrs | 500 hrs @ $400 | 10 | 1 |
26
- | **v1.0** | 2025 Jan 27 | Few hundred hrs | 1000 hrs @ $1000 | [27+](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) | [2+](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) |
27
 
28
  Training is continuous. The v0.19 model was produced "on the way" to the v1.0 model, so the Compute footprints overlap.
29
 
@@ -46,7 +46,7 @@ Most voices perform best on a "goldilocks range" of 100-200 tokens out of ~500 p
46
  The following can be run in a single cell on [Google Colab](https://colab.research.google.com/).
47
  ```py
48
  # 1️⃣ Install kokoro
49
- !pip install -q kokoro soundfile
50
  # 2️⃣ Install espeak, used for out-of-dictionary fallback
51
  !apt-get -qq -y install espeak-ng > /dev/null 2>&1
52
  # You can skip espeak installation, but OOD words will be skipped unless you provide a fallback
@@ -57,6 +57,8 @@ from IPython.display import display, Audio
57
  import soundfile as sf
58
  # 🇺🇸 'a' => American English
59
  # 🇬🇧 'b' => British English
 
 
60
  pipeline = KPipeline(lang_code='a') # make sure lang_code matches voice
61
 
62
  # The following text is for demonstration purposes only, unseen during training
@@ -67,10 +69,12 @@ It was a Sprawl voice and a Sprawl joke. The Chatsubo was a bar for professional
67
 
68
  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.
69
  '''
 
 
70
 
71
  # 4️⃣ Generate, display, and save audio files in a loop.
72
  generator = pipeline(
73
- text, voice='af_bella',
74
  speed=1, split_pattern=r'\n+'
75
  )
76
  for i, (gs, ps, audio) in enumerate(generator):
 
23
  | Model | Published | Training Data | Compute (A100 80GB) | Released Voices | Released Langs |
24
  | ----- | --------- | ------------- | ------------------- | --------------- | -------------- |
25
  | v0.19 | 2024 Dec 25 | <100 hrs | 500 hrs @ $400 | 10 | 1 |
26
+ | **v1.0** | 2025 Jan 27 | Few hundred hrs | 1000 hrs @ $1000 | [31+](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) | [3+](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md) |
27
 
28
  Training is continuous. The v0.19 model was produced "on the way" to the v1.0 model, so the Compute footprints overlap.
29
 
 
46
  The following can be run in a single cell on [Google Colab](https://colab.research.google.com/).
47
  ```py
48
  # 1️⃣ Install kokoro
49
+ !pip install -q kokoro>=0.2.3 soundfile
50
  # 2️⃣ Install espeak, used for out-of-dictionary fallback
51
  !apt-get -qq -y install espeak-ng > /dev/null 2>&1
52
  # You can skip espeak installation, but OOD words will be skipped unless you provide a fallback
 
57
  import soundfile as sf
58
  # 🇺🇸 'a' => American English
59
  # 🇬🇧 'b' => British English
60
+ # 🇫🇷 'f' => French fr-fr
61
+ # 🇮🇳 'h' => Hindi hi
62
  pipeline = KPipeline(lang_code='a') # make sure lang_code matches voice
63
 
64
  # The following text is for demonstration purposes only, unseen during training
 
69
 
70
  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.
71
  '''
72
+ # text = 'Le dromadaire resplendissant déambulait tranquillement dans les méandres en mastiquant de petites feuilles vernissées.'
73
+ # text = 'ट्रांसपोर्टरों की हड़ताल लगातार पांचवें दिन जारी, दिसंबर से इलेक्ट्रॉनिक टोल कलेक्शनल सिस्टम'
74
 
75
  # 4️⃣ Generate, display, and save audio files in a loop.
76
  generator = pipeline(
77
+ text, voice='af_bella', # <= change voice here
78
  speed=1, split_pattern=r'\n+'
79
  )
80
  for i, (gs, ps, audio) in enumerate(generator):