Add Stage 1 OpenBible benchmark comparison section with Stage 2 synthesis
Browse files
README.md
CHANGED
|
@@ -110,6 +110,27 @@ All reference audios are sourced from **[benjaminogbonna/nigerian_common_voice_d
|
|
| 110 |
|
| 111 |
---
|
| 112 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 113 |
## Repository Files
|
| 114 |
|
| 115 |
This repository contains all files necessary to run standalone synthesis or merge with standard Coqui pipelines:
|
|
|
|
| 110 |
|
| 111 |
---
|
| 112 |
|
| 113 |
+
## 🔁 Stage 1 OpenBible Benchmark Samples: Foundation vs. Conversational Comparison
|
| 114 |
+
|
| 115 |
+
These are the exact benchmark samples originally evaluated on the **[samuelolubukun/xtts-v2-igbo-openbible](https://huggingface.co/samuelolubukun/xtts-v2-igbo-openbible)** Stage 1 foundation model repository. Below, the same reference audio clips and prompt texts are synthesized side-by-side using the Stage 2 Conversational fine-tuned model to directly compare the change in cadence, natural pacing, and conversational tone:
|
| 116 |
+
|
| 117 |
+
### Stage 1 Benchmark Sample 1: *"mbize kwesiri ka e lebàra ya anya mgwamgwa ugbua"*
|
| 118 |
+
| Column 1: Original Reference Audio | Column 2: XTTS-v2 Stage 1 (OpenBible Foundation) | Column 3: XTTS-v2 Stage 2 (Conversational Adapted) |
|
| 119 |
+
| :---: | :---: | :---: |
|
| 120 |
+
| <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-openbible/resolve/main/samples/sample1_original.mp3"></audio> | <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-openbible/resolve/main/samples/sample1_synth.wav"></audio> | <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-conversational/resolve/main/samples/stage1_sample1_conversational.wav"></audio> |
|
| 121 |
+
|
| 122 |
+
### Stage 1 Benchmark Sample 2: *"Amụrụ ya na Jos, steetị Naijiria."*
|
| 123 |
+
| Column 1: Original Reference Audio | Column 2: XTTS-v2 Stage 1 (OpenBible Foundation) | Column 3: XTTS-v2 Stage 2 (Conversational Adapted) |
|
| 124 |
+
| :---: | :---: | :---: |
|
| 125 |
+
| <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-openbible/resolve/main/samples/sample2_original.mp3"></audio> | <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-openbible/resolve/main/samples/sample2_synth.wav"></audio> | <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-conversational/resolve/main/samples/stage1_sample2_conversational.wav"></audio> |
|
| 126 |
+
|
| 127 |
+
### Stage 1 Benchmark Sample 3: *"nke onye nọchitere anya ya bụ onyeisi ọrụ oyibo na steeti ahụ"*
|
| 128 |
+
| Column 1: Original Reference Audio | Column 2: XTTS-v2 Stage 1 (OpenBible Foundation) | Column 3: XTTS-v2 Stage 2 (Conversational Adapted) |
|
| 129 |
+
| :---: | :---: | :---: |
|
| 130 |
+
| <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-openbible/resolve/main/samples/sample3_original.mp3"></audio> | <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-openbible/resolve/main/samples/sample3_synth.wav"></audio> | <audio controls style="width: 250px;" src="https://huggingface.co/samuelolubukun/xtts-v2-igbo-conversational/resolve/main/samples/stage1_sample3_conversational.wav"></audio> |
|
| 131 |
+
|
| 132 |
+
---
|
| 133 |
+
|
| 134 |
## Repository Files
|
| 135 |
|
| 136 |
This repository contains all files necessary to run standalone synthesis or merge with standard Coqui pipelines:
|