Update README.md
Browse files
README.md
CHANGED
|
@@ -124,7 +124,31 @@ audio_arr = generation.cpu().numpy().squeeze()
|
|
| 124 |
sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)
|
| 125 |
```
|
| 126 |
|
| 127 |
-
You can choose a speaker from this list:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
|
| 129 |
**Tips**:
|
| 130 |
* We've set up an [inference guide](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md) to make generation faster. Think SDPA, torch.compile, batching and streaming!
|
|
|
|
| 124 |
sf.write("parler_tts_out.wav", audio_arr, model.config.sampling_rate)
|
| 125 |
```
|
| 126 |
|
| 127 |
+
You can choose a speaker from this list:
|
| 128 |
+
|
| 129 |
+
| Language | Speaker Name | Number of occurrences it was trained on |
|
| 130 |
+
|------------|--------------|-----------------------------------------|
|
| 131 |
+
| Dutch | Mark | 460066 |
|
| 132 |
+
| | Jessica | 4438 |
|
| 133 |
+
| | Michelle | 83 |
|
| 134 |
+
| French | Daniel | 10719 |
|
| 135 |
+
| | Michelle | 19 |
|
| 136 |
+
| | Christine | 20187 |
|
| 137 |
+
| | Megan | 695 |
|
| 138 |
+
| German | Nicole | 53964 |
|
| 139 |
+
| | Christopher | 1671 |
|
| 140 |
+
| | Megan | 41 |
|
| 141 |
+
| | Michelle | 12693 |
|
| 142 |
+
| Italian | Julia | 2616 |
|
| 143 |
+
| | Richard | 9640 |
|
| 144 |
+
| | Megan | 4 |
|
| 145 |
+
| Polish | Alex | 25849 |
|
| 146 |
+
| | Natalie | 9384 |
|
| 147 |
+
| Portuguese | Sophia | 34182 |
|
| 148 |
+
| | Nicholas | 4411 |
|
| 149 |
+
| Spanish | Steven | 74099 |
|
| 150 |
+
| | Olivia | 48489 |
|
| 151 |
+
| | Megan | 12 |
|
| 152 |
|
| 153 |
**Tips**:
|
| 154 |
* We've set up an [inference guide](https://github.com/huggingface/parler-tts/blob/main/INFERENCE.md) to make generation faster. Think SDPA, torch.compile, batching and streaming!
|